Last Year

2016
[1]
S. Abiteboul, G. Miklau, J. Stoyanovich, and G. Weikum, Eds., Data, Responsibly, no. 7. Schloss Dagstuhl, 2016.
Export
BibTeX
@proceedings{AbiteboulDagstuhl2016, TITLE = {Data, Responsibly (Dagstuhl Seminar 16291)}, EDITOR = {Abiteboul, Serge and Miklau, Gerome and Stoyanovich, Julia and Weikum, Gerhard}, LANGUAGE = {eng}, ISSN = {2192-5283}, URL = {urn:nbn:de:0030-drops-67644}, DOI = {10.4230/DagRep.6.7.42}, PUBLISHER = {Schloss Dagstuhl}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, PAGES = {30 p.}, SERIES = {Dagstuhl Reports}, VOLUME = {6}, ISSUE = {7}, ADDRESS = {Wadern, Germany}, }
Endnote
%0 Conference Proceedings %E Abiteboul, Serge %E Miklau, Gerome %E Stoyanovich, Julia %E Weikum, Gerhard %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Data, Responsibly : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-500A-2 %R 10.4230/DagRep.6.7.42 %U urn:nbn:de:0030-drops-67644 %I Schloss Dagstuhl %D 2016 %B Dagstuhl Seminar 16291 "Data, Responsibly" %Z date of event: 2016-07-17 - 2016-07-22 %D 2016 %C Wadern, Germany %P 30 p. %K Data responsibly, Big data, Machine bias, Data analysis, Data management, Data mining, Fairness, Diversity, Accountability, Transparency, Personal %S Dagstuhl Reports %V 6 %P 42 - 71 %@ false %U http://drops.dagstuhl.de/doku/urheberrecht1.htmlhttp://drops.dagstuhl.de/opus/volltexte/2016/6764/
[2]
K. Athukorala, D. Głowack, G. Jacucci, A. Oulasvirta, and J. Vreeken, “Is Exploratory Search Different? A Comparison of Information Search Behavior for Exploratory and Lookup Tasks,” Journal of the Association for Information Science and Technology, vol. 67, no. 11, pp. 2635–2651, 2016.
Export
BibTeX
@article{VreekenSearch2015, TITLE = {Is Exploratory Search Different? {A} Comparison of Information Search Behavior for Exploratory and Lookup Tasks}, AUTHOR = {Athukorala, Kumaripaba and G{\l}owack, Dorota and Jacucci, Giulio and Oulasvirta, Antti and Vreeken, Jilles}, LANGUAGE = {eng}, ISSN = {2330-1643}, DOI = {10.1002/asi.23617}, PUBLISHER = {Wiley}, ADDRESS = {Chichester}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Journal of the Association for Information Science and Technology}, VOLUME = {67}, NUMBER = {11}, PAGES = {2635--2651}, }
Endnote
%0 Journal Article %A Athukorala, Kumaripaba %A Głowack, Dorota %A Jacucci, Giulio %A Oulasvirta, Antti %A Vreeken, Jilles %+ External Organizations External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Is Exploratory Search Different? A Comparison of Information Search Behavior for Exploratory and Lookup Tasks : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0028-E6A7-D %R 10.1002/asi.23617 %7 2015-10-22 %D 2016 %J Journal of the Association for Information Science and Technology %V 67 %N 11 %& 2635 %P 2635 - 2651 %I Wiley %C Chichester %@ false
[3]
A. H. Baradaranshahroudi, “Fast Computation of Highest Correlated Segments in Multivariate Time-Series,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{BaradaranshahroudiMSc2016, TITLE = {Fast Computation of Highest Correlated Segments in Multivariate Time-Series}, AUTHOR = {Baradaranshahroudi, Amir Hossein}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Baradaranshahroudi, Amir Hossein %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Fast Computation of Highest Correlated Segments in Multivariate Time-Series : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5FB1-1 %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master
[4]
B. Berendt, B. Bringmann, E. Fromont, G. Garriga, P. Miettinen, N. Tatti, and V. Tresp, Eds., Machine Learning and Knowledge Discovery in Databases. Springer, 2016.
Export
BibTeX
@proceedings{ProceedingsECML2016III, TITLE = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016)}, EDITOR = {Berendt, Bettina and Bringmann, Bj{\"o}rn and Fromont, Elisa and Garriga, Gemma and Miettinen, Pauli and Tatti, Nikolai and Tresp, Volker}, LANGUAGE = {eng}, ISBN = {978-3-319-46130-4}, DOI = {10.1007/978-3-319-46131-1}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, PAGES = {XXII, 307 p.}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9853}, ADDRESS = {Riva del Garda, Italy}, }
Endnote
%0 Conference Proceedings %E Berendt, Bettina %E Bringmann, Björn %E Fromont, Elisa %E Garriga, Gemma %E Miettinen, Pauli %E Tatti, Nikolai %E Tresp, Volker %+ External Organizations External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Machine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2016 ; Riva del Garda, Italy, September 19-23, 2016 ; Proceedings, Part III %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A68E-5 %R 10.1007/978-3-319-46131-1 %@ 978-3-319-46130-4 %I Springer %D 2016 %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases %Z date of event: 2016-09-19 - 2016-09-23 %D 2016 %C Riva del Garda, Italy %P XXII, 307 p. %S Lecture Notes in Artificial Intelligence %V 9853
[5]
R. Bertens, J. Vreeken, and A. Siebes, “Keeping it Short and Simple: Summarising Complex Event Sequences with Multivariate Patterns,” in KDD’16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{BertensKDD2016, TITLE = {Keeping it Short and Simple: {S}ummarising Complex Event Sequences with Multivariate Patterns}, AUTHOR = {Bertens, Roel and Vreeken, Jilles and Siebes, Arno}, LANGUAGE = {eng}, ISBN = {978-1-4503-4232-2}, DOI = {10.1145/2939672.2939761}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {KDD'16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining}, PAGES = {735--744}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Bertens, Roel %A Vreeken, Jilles %A Siebes, Arno %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Keeping it Short and Simple: Summarising Complex Event Sequences with Multivariate Patterns : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A92D-B %R 10.1145/2939672.2939761 %D 2016 %B 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining %Z date of event: 2016-08-13 - 2016-08-17 %C San Francisco, CA, USA %B KDD'16 %P 735 - 744 %I ACM %@ 978-1-4503-4232-2
[6]
A. Bhattacharyya, “Squish: Efficiently Summarising Sequences with Rich and Interleaving Patterns,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{BhattacharyyaMSc2016, TITLE = {Squish: Efficiently Summarising Sequences with Rich and Interleaving Patterns}, AUTHOR = {Bhattacharyya, Apratim}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Bhattacharyya, Apratim %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Squish: Efficiently Summarising Sequences with Rich and Interleaving Patterns : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F37-4 %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master
[7]
J. A. Biega, K. P. Gummadi, I. Mele, D. Milchevski, C. Tryfonopoulos, and G. Weikum, “R-Susceptibility: An IR-Centric Approach to Assessing Privacy Risks for Users in Online Communities,” in SIGIR’16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Italy, 2016.
Export
BibTeX
@inproceedings{BiegaSIGIR2016, TITLE = {R-Susceptibility: {A}n {IR}-Centric Approach to Assessing Privacy Risks for Users in Online Communities}, AUTHOR = {Biega, Joanna Asia and Gummadi, Krishna P. and Mele, Ida and Milchevski, Dragan and Tryfonopoulos, Christos and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4069-4}, DOI = {10.1145/2911451.2911533}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {SIGIR'16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval}, PAGES = {365--374}, ADDRESS = {Pisa, Italy}, }
Endnote
%0 Conference Proceedings %A Biega, Joanna Asia %A Gummadi, Krishna P. %A Mele, Ida %A Milchevski, Dragan %A Tryfonopoulos, Christos %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T R-Susceptibility: An IR-Centric Approach to Assessing Privacy Risks for Users in Online Communities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A921-3 %R 10.1145/2911451.2911533 %D 2016 %B 39th International ACM SIGIR Conference on Research and Development in Information Retrieval %Z date of event: 2016-07-17 - 2016-07-21 %C Pisa, Italy %B SIGIR'16 %P 365 - 374 %I ACM %@ 978-1-4503-4069-4
[8]
T. Bögel, E. Gius, J. Jacke, and J. Strötgen, “From Order to Order Switch: Mediating between Complexity and Reproducibility in the Context of Automated Literary Annotation,” in Digital Humanities 2016 (DH 2016), Krakow, Poland, 2016.
Export
BibTeX
@inproceedings{BoegelDH2016, TITLE = {From Order to Order Switch: {M}ediating between Complexity and Reproducibility in the Context of Automated Literary Annotation}, AUTHOR = {B{\"o}gel, Thomas and Gius, Evelyn and Jacke, Janina and Str{\"o}tgen, Jannik}, LANGUAGE = {eng}, URL = {http://dh2016.adho.org/abstracts/275}, PUBLISHER = {Jagiellonian University \& Pedagogical University}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Digital Humanities 2016 (DH 2016)}, PAGES = {379--382}, ADDRESS = {Krakow, Poland}, }
Endnote
%0 Conference Proceedings %A Bögel, Thomas %A Gius, Evelyn %A Jacke, Janina %A Strötgen, Jannik %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T From Order to Order Switch: Mediating between Complexity and Reproducibility in the Context of Automated Literary Annotation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0E96-0 %D 2016 %B Digital Humanities %Z date of event: 2016-07-11 - 2016-07-16 %C Krakow, Poland %B Digital Humanities 2016 %P 379 - 382 %I Jagiellonian University & Pedagogical University %U http://dh2016.adho.org/abstracts/275
[9]
N. Boldyrev, M. Spaniol, and G. Weikum, “ACROSS: A Framework for Multi-Cultural Interlinking of Web Taxonomies,” in WebSci’16, ACM Web Science Conference, Hannover, Germany, 2016.
Export
BibTeX
@inproceedings{BoldryevWebSci2016, TITLE = {{ACROSS}: {A} Framework for Multi-Cultural Interlinking of {W}eb Taxonomies}, AUTHOR = {Boldyrev, Natalia and Spaniol, Marc and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4208-7}, DOI = {10.1145/2908131.2908164}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WebSci'16, ACM Web Science Conference}, PAGES = {127--136}, ADDRESS = {Hannover, Germany}, }
Endnote
%0 Conference Proceedings %A Boldyrev, Natalia %A Spaniol, Marc %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T ACROSS: A Framework for Multi-Cultural Interlinking of Web Taxonomies : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-01B6-E %R 10.1145/2908131.2908164 %D 2016 %B ACM Web Science Conference %Z date of event: 2016-05-22 - 2016-05-25 %C Hannover, Germany %B WebSci'16 %P 127 - 136 %I ACM %@ 978-1-4503-4208-7
[10]
P. Chau, J. Vreeken, M. van Leeuwen, D. Shahaf, and C. Faloutsos, Eds., Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics. IDEA’16, 2016.
Export
BibTeX
@proceedings{ChauIDEA2016, TITLE = {Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics (IDEA 2016)}, EDITOR = {Chau, Polo and Vreeken, Jilles and van Leeuwen, Matthijs and Shahaf, Dafna and Faloutsos, Christons}, LANGUAGE = {eng}, PUBLISHER = {IDEA'16}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, PAGES = {137 p.}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %E Chau, Polo %E Vreeken, Jilles %E van Leeuwen, Matthijs %E Shahaf, Dafna %E Faloutsos , Christons %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2439-4 %I IDEA'16 %D 2016 %B ACM SIGKDD 2016 Full-day Workshop on Interactive Data Exploration and Analytics %Z date of event: 2016-08-14 - 2016-08-14 %D 2016 %C San Francisco, CA, USA %P 137 p.
[11]
J. Chen, N. Tandon, C. D. Hariman, and G. de Melo, “WebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge,” in The Semantic Web -- ISWC 2016, Kobe, Japan, 2016.
Export
BibTeX
@inproceedings{ChenISWC2016, TITLE = {{WebBrain}: {J}oint Neural Learning of Large-Scale Commonsense Knowledge}, AUTHOR = {Chen, Jiaqiang and Tandon, Niket and Hariman, Charles Darwis and de Melo, Gerard}, LANGUAGE = {eng}, ISBN = {978-3-319-46522-7}, DOI = {10.1007/978-3-319-46523-4_7}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {The Semantic Web -- ISWC 2016}, EDITOR = {Groth, Paul and Simperl, Elena and Gray, Alasdair and Sabou, Marta and Kr{\"o}tzsch, Markus and Lecue, Freddy and Fl{\"o}ck, Fabian and Gil, Yolanda}, PAGES = {102--118}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9981}, ADDRESS = {Kobe, Japan}, }
Endnote
%0 Conference Proceedings %A Chen, Jiaqiang %A Tandon, Niket %A Hariman, Charles Darwis %A de Melo, Gerard %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T WebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2DED-A %R 10.1007/978-3-319-46523-4_7 %D 2016 %B 15th International Semantic Web Conference %Z date of event: 2016-10-17 - 2016-10-21 %C Kobe, Japan %B The Semantic Web -- ISWC 2016 %E Groth, Paul; Simperl, Elena; Gray, Alasdair; Sabou, Marta; Krötzsch, Markus; Lecue, Freddy; Flöck, Fabian; Gil, Yolanda %P 102 - 118 %I Springer %@ 978-3-319-46522-7 %B Lecture Notes in Computer Science %N 9981
[12]
C. X. Chu, “Mining How-to Task Knowledge from Online Communities,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{ChuMSc2016, TITLE = {Mining How-to Task Knowledge from Online Communities}, AUTHOR = {Chu, Cuong Xuan}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Chu, Cuong Xuan %Y Weikum, Gerhard %A referee: Vreeken, Jilles %A referee: Tandon, Niket %+ Databases and Information Systems, MPI for Informatics, Max Planck Society International Max Planck Research School, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Mining How-to Task Knowledge from Online Communities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-491D-B %I Universität des Saarlandes %C Saarbrücken %D 2016 %P 66 p. %V master %9 master
[13]
L. Del Corro, “Methods for Open Information Extraction and Sense Disambiguation on Natural Language Text,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@phdthesis{delcorrophd15, TITLE = {Methods for Open Information Extraction and Sense Disambiguation on Natural Language Text}, AUTHOR = {Del Corro, Luciano}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Del Corro, Luciano %Y Gemulla, Rainer %A referee: Ponzetto, Simone Paolo %+ Databases and Information Systems, MPI for Informatics, Max Planck Society International Max Planck Research School, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Methods for Open Information Extraction and Sense Disambiguation on Natural Language Text : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-B3DB-3 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P xiv, 101 p. %V phd %9 phd %U http://scidok.sulb.uni-saarland.de/volltexte/2016/6346/http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=de
[14]
G. de Melo and N. Tandon, “Seeing is Believing: The Quest for Multimodal Knowledge,” ACM SIGWEB Newsletter, no. Spring, 2016.
Export
BibTeX
@article{DemeloTandon:SIGWEB2016, TITLE = {Seeing is Believing: {T}he Quest for Multimodal Knowledge}, AUTHOR = {de Melo, Gerard and Tandon, Niket}, LANGUAGE = {eng}, DOI = {10.1145/2903513.2903517}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, JOURNAL = {ACM SIGWEB Newsletter}, NUMBER = {Spring}, EID = {4}, }
Endnote
%0 Journal Article %A de Melo, Gerard %A Tandon, Niket %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Seeing is Believing: The Quest for Multimodal Knowledge : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-54BB-3 %R 10.1145/2903513.2903517 %7 2016 %D 2016 %J ACM SIGWEB Newsletter %N Spring %Z sequence number: 4 %I ACM %C New York, NY
[15]
L. Derczynski, J. Strötgen, D. Maynard, M. A. Greenwood, and M. Jung, “GATE-Time: Extraction of Temporal Expressions and Event,” in Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia, 2016.
Export
BibTeX
@inproceedings{DERCZYNSKI16.915, TITLE = {{GATE}-Time: {E}xtraction of Temporal Expressions and Event}, AUTHOR = {Derczynski, Leon and Str{\"o}tgen, Jannik and Maynard, Diana and Greenwood, Mark A. and Jung, Manuel}, LANGUAGE = {eng}, ISBN = {978-2-9517408-9-1}, PUBLISHER = {European Language Resources Association (ELRA)}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, EDITOR = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Goggi, Sara and Grobelnik, Marko and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asunci{\'o}n and Odijk, Jan and Piperidis, Stelios}, PAGES = {3702--3708}, EID = {915}, ADDRESS = {Portoro{\v z}, Slovenia}, }
Endnote
%0 Conference Proceedings %A Derczynski, Leon %A Strötgen, Jannik %A Maynard, Diana %A Greenwood, Mark A. %A Jung, Manuel %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T GATE-Time: Extraction of Temporal Expressions and Event : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-4139-8 %D 2016 %B 10th Language Resources and Evaluation Conference %Z date of event: 2016-05-23 - 2016-05-28 %C Portorož, Slovenia %B Tenth International Conference on Language Resources and Evaluation %E Calzolari, Nicoletta; Choukri, Khalid; Declerck, Thierry; Goggi, Sara; Grobelnik, Marko; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Moreno, Asunción; Odijk, Jan; Piperidis, Stelios %P 3702 - 3708 %Z sequence number: 915 %I European Language Resources Association (ELRA) %@ 978-2-9517408-9-1
[16]
H. Dombrowski, “Boolean Tensor Decomposition based on the Walk’n'Merge Algorithm,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{DombrowskiMaster2016, TITLE = {Boolean Tensor Decomposition based on the Walk'n'Merge Algorithm}, AUTHOR = {Dombrowski, Helge}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Dombrowski, Helge %Y Miettinen, Pauli %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Boolean Tensor Decomposition based on the Walk'n'Merge Algorithm : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2280-1 %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master
[17]
X. Du, O. Emebo, A. Varde, N. Tandon, S. N. Chowdhury, and G. Weikum, “Air Quality Assessment from Social Media and Structured Data: Pollutants and Health Impacts in Urban Planning,” in Proceedings of the 2016 IEEE 32nd International Conference on Data Engineering Workshops (ICDEW 2016), Helsinki, Finland, 2016.
Export
BibTeX
@inproceedings{DuICDEW2016, TITLE = {Air Quality Assessment from Social Media and Structured Data: {P}ollutants and Health Impacts in Urban Planning}, AUTHOR = {Du, Xu and Emebo, Onyeka and Varde, Aparna and Tandon, Niket and Chowdhury, Sreyasi Nag and Weikum, Gerhard}, LANGUAGE = {eng}, DOI = {10.1109/ICDEW.2016.7495616}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Proceedings of the 2016 IEEE 32nd International Conference on Data Engineering Workshops (ICDEW 2016)}, PAGES = {54--59}, ADDRESS = {Helsinki, Finland}, }
Endnote
%0 Conference Proceedings %A Du, Xu %A Emebo, Onyeka %A Varde, Aparna %A Tandon, Niket %A Chowdhury, Sreyasi Nag %A Weikum, Gerhard %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Air Quality Assessment from Social Media and Structured Data: Pollutants and Health Impacts in Urban Planning : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-01AE-2 %R 10.1109/ICDEW.2016.7495616 %D 2016 %B IEEE 32nd International Conference on Data Engineering Workshops %Z date of event: 2016-05-16 - 2016-05-20 %C Helsinki, Finland %B Proceedings of the 2016 IEEE 32nd International Conference on Data Engineering Workshops %P 54 - 59 %I IEEE
[18]
P. Ernst, A. Siu, D. Milchevski, J. Hoffart, and G. Weikum, “DeepLife: An Entity-aware Search, Analytics and Exploration Platform for Health and Life Sciences,” in Proceedings of ACL-2016 System Demonstrations, Berlin, Germany, 2016.
Export
BibTeX
@inproceedings{ernst-EtAl:2016:P16-4, TITLE = {{DeepLife:} {A}n Entity-aware Search, Analytics and Exploration Platform for Health and Life Sciences}, AUTHOR = {Ernst, Patrick and Siu, Amy and Milchevski, Dragan and Hoffart, Johannes and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-945626-0}, DOI = {10.18653/v1/P16-4004}, PUBLISHER = {ACL}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of ACL-2016 System Demonstrations}, EDITOR = {Pradhan, Sameer and Apidianaki, Marianna}, PAGES = {19--24}, ADDRESS = {Berlin, Germany}, }
Endnote
%0 Conference Proceedings %A Ernst, Patrick %A Siu, Amy %A Milchevski, Dragan %A Hoffart, Johannes %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T DeepLife: An Entity-aware Search, Analytics and Exploration Platform for Health and Life Sciences : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-24CA-F %R 10.18653/v1/P16-4004 %D 2016 %B The 54th Annual Meeting of the Association for Computational Linguistics %Z date of event: 2016-08-07 - 2016-08-12 %C Berlin, Germany %B Proceedings of ACL-2016 System Demonstrations %E Pradhan, Sameer; Apidianaki, Marianna %P 19 - 24 %I ACL %@ 978-1-945626-0
[19]
P. Frasconi, N. Landwehr, G. Manco, and J. Vreeken, Eds., Machine Learning and Knowledge Discovery in Databases. Springer, 2016.
Export
BibTeX
@proceedings{ProceedingsECML2016I, TITLE = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016)}, EDITOR = {Frasconi, Paolo and Landwehr, Niels and Manco, Guiseppe and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-3-319-46127-4}, DOI = {10.1007/978-3-319-46128-1}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, PAGES = {XXXVI, 817 p.}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9851}, ADDRESS = {Riva del Garda, Italy}, }
Endnote
%0 Conference Proceedings %E Frasconi, Paolo %E Landwehr, Niels %E Manco, Guiseppe %E Vreeken, Jilles %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Machine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2016 ; Riva del Garda, Italy, September 19-23, 2016 ; Proceedings, Part I %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A68A-D %R 10.1007/978-3-319-46128-1 %@ 978-3-319-46127-4 %I Springer %D 2016 %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases %Z date of event: 2016-09-19 - 2016-09-23 %D 2016 %C Riva del Garda, Italy %P XXXVI, 817 p. %S Lecture Notes in Artificial Intelligence %V 9851
[20]
P. Frasconi, N. Landwehr, G. Manco, and J. Vreeken, Eds., Machine Learning and Knowledge Discovery in Databases. Springer, 2016.
Export
BibTeX
@proceedings{ProceedingsECML2016, TITLE = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016)}, EDITOR = {Frasconi, Paolo and Landwehr, Niels and Manco, Guiseppe and Vreeken, Jilles}, LANGUAGE = {eng}, DOI = {10.1007/978-3-319-46227-1}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, PAGES = {XXVIII, 825 p.}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9852}, ADDRESS = {Riva del Garda, Italy}, }
Endnote
%0 Conference Proceedings %E Frasconi, Paolo %E Landwehr, Niels %E Manco, Guiseppe %E Vreeken, Jilles %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Machine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2016 ; Riva del Garda, Italy, September 19-23, 2016 ; Proceedings, Part II %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A688-2 %R 10.1007/978-3-319-46227-1 %I Springer %D 2016 %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases %Z date of event: 2016-09-19 - 2016-09-23 %D 2016 %C Riva del Garda, Italy %P XXVIII, 825 p. %S Lecture Notes in Artificial Intelligence %V 9852
[21]
M. H. Gad-Elrab, D. Stepanova, J. Urbani, and G. Weikum, “Exception-Enriched Rule Learning from Knowledge Graphs,” in KI 2016: Advances in Artificial Intelligence, Klagenfurt, Austria, 2016.
Export
BibTeX
@inproceedings{Gad-ElrabKI2016, TITLE = {Exception-Enriched Rule Learning from Knowledge Graphs}, AUTHOR = {Gad-Elrab, Mohamed H. and Stepanova, Daria and Urbani, Jacopo and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-3-319-46072-7}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {KI 2016: Advances in Artificial Intelligence}, EDITOR = {Friedrich, Gerhard and Helmert, Malte and Wotawa, Franz}, PAGES = {211--217}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9904}, ADDRESS = {Klagenfurt, Austria}, }
Endnote
%0 Conference Proceedings %A Gad-Elrab, Mohamed H. %A Stepanova, Daria %A Urbani, Jacopo %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Exception-Enriched Rule Learning from Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-22E9-A %D 2016 %B 39th Annual German Conference on AI %Z date of event: 2016-09-26 - 2016-09-30 %C Klagenfurt, Austria %B KI 2016: Advances in Artificial Intelligence %E Friedrich, Gerhard; Helmert, Malte; Wotawa, Franz %P 211 - 217 %I Springer %@ 978-3-319-46072-7 %B Lecture Notes in Artificial Intelligence %N 9904
[22]
M. H. Gad-Elrab, D. Stepanova, J. Urbani, and G. Weikum, “Exception-Enriched Rule Learning from Knowledge Graphs,” in The Semantic Web -- ISWC 2016, Kobe, Japan, 2016.
Export
BibTeX
@inproceedings{Gad-ElrabISWC2016, TITLE = {Exception-Enriched Rule Learning from Knowledge Graphs}, AUTHOR = {Gad-Elrab, Mohamed H. and Stepanova, Daria and Urbani, Jacopo and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-3-319-46522-7}, DOI = {10.1007/978-3-319-46523-4_15}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {The Semantic Web -- ISWC 2016}, EDITOR = {Groth, Paul and Simperl, Elena and Gray, Alasdair and Sabou, Marta and Kr{\"o}tzsch, Markus and Lecue, Freddy and Fl{\"o}ck, Fabian and Gil, Yolanda}, PAGES = {234--251}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9981}, ADDRESS = {Kobe, Japan}, }
Endnote
%0 Conference Proceedings %A Gad-Elrab, Mohamed H. %A Stepanova, Daria %A Urbani, Jacopo %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Exception-Enriched Rule Learning from Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A91F-B %R 10.1007/978-3-319-46523-4_15 %D 2016 %B 15th International Semantic Web Conference %Z date of event: 2016-10-17 - 2016-10-21 %C Kobe, Japan %B The Semantic Web -- ISWC 2016 %E Groth, Paul; Simperl, Elena; Gray, Alasdair; Sabou, Marta; Krötzsch, Markus; Lecue, Freddy; Flöck, Fabian; Gil, Yolanda %P 234 - 251 %I Springer %@ 978-3-319-46522-7 %B Lecture Notes in Computer Science %N 9981
[23]
E. Galbrun and P. Miettinen, “Mining Redescriptions with Siren,” ACM Transactions on Knowledge Discovery from Data. (Accepted/in press)
Export
BibTeX
@article{galbrun17mining, TITLE = {Mining Redescriptions with {Siren}}, AUTHOR = {Galbrun, Esther and Miettinen, Pauli}, LANGUAGE = {eng}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, JOURNAL = {ACM Transactions on Knowledge Discovery from Data}, }
Endnote
%0 Journal Article %A Galbrun, Esther %A Miettinen, Pauli %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Mining Redescriptions with Siren : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-227B-F %D 2016 %J ACM Transactions on Knowledge Discovery from Data %I ACM %C New York, NY
[24]
M. Gandhi, “Towards Summarising Large Transaction Databases,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{GandhiMSc2016, TITLE = {Towards Summarising Large Transaction Databases}, AUTHOR = {Gandhi, Manan}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Gandhi, Manan %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Towards Summarising Large Transaction Databases : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F61-4 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P X, 55 p. %V master %9 master
[25]
K. Grosse, “An Approach for Ontological Pattern-based Summarization,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{GrosseMSc2016, TITLE = {An Approach for Ontological Pattern-based Summarization}, AUTHOR = {Grosse, Kathrin}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Grosse, Kathrin %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T An Approach for Ontological Pattern-based Summarization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F5F-C %I Universität des Saarlandes %C Saarbrücken %D 2016 %P X, 84 p. %V master %9 master
[26]
A. Grycner and G. Weikum, “POLY: Mining Relational Paraphrases from Multilingual Sentences,” in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), Austin, TX, USA, 2016.
Export
BibTeX
@inproceedings{GrycnerENMLP2016, TITLE = {{POLY}: {M}ining Relational Paraphrases from Multilingual Sentences}, AUTHOR = {Grycner, Adam and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-945626-25-8}, URL = {https://aclweb.org/anthology/D16-1236}, PUBLISHER = {ACL}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016)}, PAGES = {2183--2192}, ADDRESS = {Austin, TX, USA}, }
Endnote
%0 Conference Proceedings %A Grycner, Adam %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T POLY: Mining Relational Paraphrases from Multilingual Sentences : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-158D-0 %U https://aclweb.org/anthology/D16-1236 %D 2016 %B Conference on Empirical Methods in Natural Language Processing %Z date of event: 2016-11-01 - 2016-11-05 %C Austin, TX, USA %B Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing %P 2183 - 2192 %I ACL %@ 978-1-945626-25-8
[27]
D. Gupta, “Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search and Analytics,” 2016. [Online]. Available: http://arxiv.org/abs/1603.00260. (arXiv: 1603.00260)
Abstract
In this article, I present the questions that I seek to answer in my PhD research. I posit to analyze natural language text with the help of semantic annotations and mine important events for navigating large text corpora. Semantic annotations such as named entities, geographic locations, and temporal expressions can help us mine events from the given corpora. These events thus provide us with useful means to discover the locked knowledge in them. I pose three problems that can help unlock this knowledge vault in semantically annotated text corpora: i. identifying important events; ii. semantic search; and iii. event analytics.
Export
BibTeX
@online{Gupta1603.00260, TITLE = {Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search and Analytics}, AUTHOR = {Gupta, Dhruv}, URL = {http://arxiv.org/abs/1603.00260}, DOI = {10.1145/2835776.2855083}, EPRINT = {1603.00260}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {In this article, I present the questions that I seek to answer in my PhD research. I posit to analyze natural language text with the help of semantic annotations and mine important events for navigating large text corpora. Semantic annotations such as named entities, geographic locations, and temporal expressions can help us mine events from the given corpora. These events thus provide us with useful means to discover the locked knowledge in them. I pose three problems that can help unlock this knowledge vault in semantically annotated text corpora: i. identifying important events; ii. semantic search; and iii. event analytics.}, }
Endnote
%0 Report %A Gupta, Dhruv %+ Databases and Information Systems, MPI for Informatics, Max Planck Society %T Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search and Analytics : %U http://hdl.handle.net/11858/00-001M-0000-002C-2224-4 %R 10.1145/2835776.2855083 %U http://arxiv.org/abs/1603.00260 %D 2016 %X In this article, I present the questions that I seek to answer in my PhD research. I posit to analyze natural language text with the help of semantic annotations and mine important events for navigating large text corpora. Semantic annotations such as named entities, geographic locations, and temporal expressions can help us mine events from the given corpora. These events thus provide us with useful means to discover the locked knowledge in them. I pose three problems that can help unlock this knowledge vault in semantically annotated text corpora: i. identifying important events; ii. semantic search; and iii. event analytics. %K Computer Science, Information Retrieval, cs.IR,Computer Science, Computation and Language, cs.CL
[28]
D. Gupta, “Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search & Analytics,” in WSDM’16, 9th ACM International Conference on Web Search and Data Mining, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{GuptaWSDM2016, TITLE = {Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search \& Analytics}, AUTHOR = {Gupta, Dhruv}, LANGUAGE = {eng}, ISBN = {978-1-4503-3716-8}, DOI = {10.1145/2835776.2855083}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WSDM'16, 9th ACM International Conference on Web Search and Data Mining}, PAGES = {705--705}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Gupta, Dhruv %+ Databases and Information Systems, MPI for Informatics, Max Planck Society %T Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search & Analytics : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-7526-7 %R 10.1145/2835776.2855083 %D 2016 %B 9th ACM International Conference on Web Search and Data Mining %Z date of event: 2016-02-22 - 2016-02-25 %C San Francisco, CA, USA %B WSDM'16 %P 705 - 705 %I ACM %@ 978-1-4503-3716-8
[29]
D. Gupta and K. Berberich, “Diversifying Search Results Using Time: An Information Retrieval Method for Historians,” in Advances in Information Retrieval (ECIR 2016), Padova, Italy, 2016.
Export
BibTeX
@inproceedings{GuptaECIR2016, TITLE = {Diversifying Search Results Using Time: An Information Retrieval Method for Historians}, AUTHOR = {Gupta, Dhruv and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-3-319-30670-4}, DOI = {10.1007/978-3-319-30671-1_69}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Advances in Information Retrieval (ECIR 2016)}, EDITOR = {Ferro, Nicola and Crestani, Fabio and Moens, Marie-Francine and Mothe, Josiane and Silvestre, Fabrizio and Di Nunzio, Giorgio Maria and Hauff, Claudia and Silvello, Gianmaria}, PAGES = {789--795}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9626}, ADDRESS = {Padova, Italy}, }
Endnote
%0 Conference Proceedings %A Gupta, Dhruv %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Diversifying Search Results Using Time: An Information Retrieval Method for Historians : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-7514-F %R 10.1007/978-3-319-30671-1_69 %D 2016 %B 38th European Conference on Information Retrieval %Z date of event: 2016-03-20 - 2016-03-23 %C Padova, Italy %B Advances in Information Retrieval %E Ferro, Nicola; Crestani, Fabio; Moens, Marie-Francine; Mothe, Josiane; Silvestre, Fabrizio; Di Nunzio, Giorgio Maria; Hauff, Claudia; Silvello, Gianmaria %P 789 - 795 %I Springer %@ 978-3-319-30670-4 %B Lecture Notes in Computer Science %N 9626
[30]
D. Gupta and K. Berberich, “A Probabilistic Framework for Time-Sensitive Search,” in Proceedings of the 12th NTCIR Conference on Evaluation of Information Access Technologies, Tokyo, Japan, 2016.
Export
BibTeX
@inproceedings{GuptaNTCIR12, TITLE = {A Probabilistic Framework for Time-Sensitive Search}, AUTHOR = {Gupta, Dhruv and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-4-86049-071-3}, URL = {http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings12/NTCIR/toc_ntcir.html}, PUBLISHER = {National Institute of Informatics}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the 12th NTCIR Conference on Evaluation of Information Access Technologies}, DEBUG = {author: Yamamoto, Shuhei}, EDITOR = {Kando, Noriko and Kishida, Kazuaki and Kato, Makoto P.}, PAGES = {225--232}, ADDRESS = {Tokyo, Japan}, }
Endnote
%0 Conference Proceedings %A Gupta, Dhruv %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T A Probabilistic Framework for Time-Sensitive Search : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2238-7 %U http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings12/NTCIR/toc_ntcir.html %D 2016 %B 12th NTCIR Conference on Evaluation of Information Access Technologies %Z date of event: 2016-06-07 - 2016-06-10 %C Tokyo, Japan %B Proceedings of the 12th NTCIR Conference on Evaluation of Information Access Technologies %E Kando, Noriko; Kishida, Kazuaki; Kato, Makoto P.; Yamamoto, Shuhei %P 225 - 232 %I National Institute of Informatics %@ 978-4-86049-071-3
[31]
D. Gupta and K. Berberich, “Diversifying Search Results Using Time,” Max-Planck-Institut für Informatik, Saarbrücken, MPI-I-2016-5-001, 2016.
Abstract
Getting an overview of a historic entity or event can be difficult in search results, especially if important dates concerning the entity or event are not known beforehand. For such information needs, users would benefit if returned results covered diverse dates, thus giving an overview of what has happened throughout history. Diversifying search results based on important dates can be a building block for applications, for instance, in digital humanities. Historians would thus be able to quickly explore longitudinal document collections by querying for entities or events without knowing associated important dates apriori. In this work, we describe an approach to diversify search results using temporal expressions (e.g., in the 1990s) from their contents. Our approach first identifies time intervals of interest to the given keyword query based on pseudo-relevant documents. It then re-ranks query results so as to maximize the coverage of identified time intervals. We present a novel and objective evaluation for our proposed approach. We test the effectiveness of our methods on the New York Times Annotated corpus and the Living Knowledge corpus, collectively consisting of around 6 million documents. Using history-oriented queries and encyclopedic resources we show that our method indeed is able to present search results diversified along time.
Export
BibTeX
@techreport{GuptaReport2016-5-001, TITLE = {Diversifying Search Results Using Time}, AUTHOR = {Gupta, Dhruv and Berberich, Klaus}, LANGUAGE = {eng}, ISSN = {0946-011X}, NUMBER = {MPI-I-2016-5-001}, INSTITUTION = {Max-Planck-Institut f{\"u}r Informatik}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Getting an overview of a historic entity or event can be difficult in search results, especially if important dates concerning the entity or event are not known beforehand. For such information needs, users would benefit if returned results covered diverse dates, thus giving an overview of what has happened throughout history. Diversifying search results based on important dates can be a building block for applications, for instance, in digital humanities. Historians would thus be able to quickly explore longitudinal document collections by querying for entities or events without knowing associated important dates apriori. In this work, we describe an approach to diversify search results using temporal expressions (e.g., in the 1990s) from their contents. Our approach first identifies time intervals of interest to the given keyword query based on pseudo-relevant documents. It then re-ranks query results so as to maximize the coverage of identified time intervals. We present a novel and objective evaluation for our proposed approach. We test the effectiveness of our methods on the New York Times Annotated corpus and the Living Knowledge corpus, collectively consisting of around 6 million documents. Using history-oriented queries and encyclopedic resources we show that our method indeed is able to present search results diversified along time.}, TYPE = {Research Report}, }
Endnote
%0 Report %A Gupta, Dhruv %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Diversifying Search Results Using Time : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-0AA4-C %Y Max-Planck-Institut für Informatik %C Saarbrücken %D 2016 %P 51 p. %X Getting an overview of a historic entity or event can be difficult in search results, especially if important dates concerning the entity or event are not known beforehand. For such information needs, users would benefit if returned results covered diverse dates, thus giving an overview of what has happened throughout history. Diversifying search results based on important dates can be a building block for applications, for instance, in digital humanities. Historians would thus be able to quickly explore longitudinal document collections by querying for entities or events without knowing associated important dates apriori. In this work, we describe an approach to diversify search results using temporal expressions (e.g., in the 1990s) from their contents. Our approach first identifies time intervals of interest to the given keyword query based on pseudo-relevant documents. It then re-ranks query results so as to maximize the coverage of identified time intervals. We present a novel and objective evaluation for our proposed approach. We test the effectiveness of our methods on the New York Times Annotated corpus and the Living Knowledge corpus, collectively consisting of around 6 million documents. Using history-oriented queries and encyclopedic resources we show that our method indeed is able to present search results diversified along time. %B Research Report %@ false
[32]
D. Gupta, J. Strötgen, and K. Berberich, “DIGITALHISTORIAN: Search & Analytics Using Annotations,” in HistoInformatics 2016, The 3rd HistoInformatics Workshop on Computational History, Krakow, Poland, 2016.
Export
BibTeX
@inproceedings{Gupta, TITLE = {{DIGITALHISTORIAN}: {S}earch \& Analytics Using Annotations}, AUTHOR = {Gupta, Dhruv and Str{\"o}tgen, Jannik and Berberich, Klaus}, LANGUAGE = {eng}, ISSN = {1613-0073}, URL = {urn:nbn:de:0074-1632-7}, PUBLISHER = {CEUR-WS.org}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {HistoInformatics 2016, The 3rd HistoInformatics Workshop on Computational History}, EDITOR = {D{\"u}ring, Marten and Jatowt, Adam and Preiser-Kappeller, Johannes and van Den Bosch, Antal}, PAGES = {5--10}, SERIES = {CEUR Workshop Proceedings}, VOLUME = {1632}, ADDRESS = {Krakow, Poland}, }
Endnote
%0 Conference Proceedings %A Gupta, Dhruv %A Strötgen, Jannik %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T DIGITALHISTORIAN: Search & Analytics Using Annotations : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0885-2 %D 2016 %B The 3rd HistoInformatics Workshop on Computational History %Z date of event: 2016-07-11 - 2016-07-11 %C Krakow, Poland %B HistoInformatics 2016 %E Düring, Marten; Jatowt, Adam; Preiser-Kappeller, Johannes; van Den Bosch, Antal %P 5 - 10 %I CEUR-WS.org %B CEUR Workshop Proceedings %N 1632 %@ false %U http://ceur-ws.org/Vol-1632/paper_1.pdf
[33]
D. Gupta, J. Strötgen, and K. Berberich, “EventMiner: Mining Events from Annotated Documents,” in ICTIR’2016, ACM International Conference on the Theory of Information Retrieval, Newark, DE, USA, 2016.
Export
BibTeX
@inproceedings{GuptaICTIR2016, TITLE = {{EventMiner}: {M}ining Events from Annotated Documents}, AUTHOR = {Gupta, Dhruv and Str{\"o}tgen, Jannik and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-1-4503-4497-5}, DOI = {10.1145/2970398.2970411}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {ICTIR'2016, ACM International Conference on the Theory of Information Retrieval}, PAGES = {261--270}, ADDRESS = {Newark, DE, USA}, }
Endnote
%0 Conference Proceedings %A Gupta, Dhruv %A Strötgen, Jannik %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T EventMiner: Mining Events from Annotated Documents : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-B262-0 %R 10.1145/2970398.2970411 %D 2016 %B ACM International Conference on the Theory of Information Retrieval %Z date of event: 2016-09-12 - 2016-09-16 %C Newark, DE, USA %B ICTIR'2016 %P 261 - 270 %I ACM %@ 978-1-4503-4497-5
[34]
S. Gurajada and M. Theobald, “Distributed Processing of Generalized Graph-Pattern Queries in SPARQL 1.1,” 2016. [Online]. Available: http://arxiv.org/abs/1609.05293. (arXiv: 1609.05293)
Abstract
We propose an efficient and scalable architecture for processing generalized graph-pattern queries as they are specified by the current W3C recommendation of the SPARQL 1.1 "Query Language" component. Specifically, the class of queries we consider consists of sets of SPARQL triple patterns with labeled property paths. From a relational perspective, this class resolves to conjunctive queries of relational joins with additional graph-reachability predicates. For the scalable, i.e., distributed, processing of this kind of queries over very large RDF collections, we develop a suitable partitioning and indexing scheme, which allows us to shard the RDF triples over an entire cluster of compute nodes and to process an incoming SPARQL query over all of the relevant graph partitions (and thus compute nodes) in parallel. Unlike most prior works in this field, we specifically aim at the unified optimization and distributed processing of queries consisting of both relational joins and graph-reachability predicates. All communication among the compute nodes is established via a proprietary, asynchronous communication protocol based on the Message Passing Interface.
Export
BibTeX
@online{Gurajada1609.05293, TITLE = {Distributed Processing of Generalized Graph-Pattern Queries in {SPARQL} 1.1}, AUTHOR = {Gurajada, Sairam and Theobald, Martin}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1609.05293}, EPRINT = {1609.05293}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We propose an efficient and scalable architecture for processing generalized graph-pattern queries as they are specified by the current W3C recommendation of the SPARQL 1.1 "Query Language" component. Specifically, the class of queries we consider consists of sets of SPARQL triple patterns with labeled property paths. From a relational perspective, this class resolves to conjunctive queries of relational joins with additional graph-reachability predicates. For the scalable, i.e., distributed, processing of this kind of queries over very large RDF collections, we develop a suitable partitioning and indexing scheme, which allows us to shard the RDF triples over an entire cluster of compute nodes and to process an incoming SPARQL query over all of the relevant graph partitions (and thus compute nodes) in parallel. Unlike most prior works in this field, we specifically aim at the unified optimization and distributed processing of queries consisting of both relational joins and graph-reachability predicates. All communication among the compute nodes is established via a proprietary, asynchronous communication protocol based on the Message Passing Interface.}, }
Endnote
%0 Report %A Gurajada, Sairam %A Theobald, Martin %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Distributed Processing of Generalized Graph-Pattern Queries in SPARQL 1.1 : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2212-C %U http://arxiv.org/abs/1609.05293 %D 2016 %X We propose an efficient and scalable architecture for processing generalized graph-pattern queries as they are specified by the current W3C recommendation of the SPARQL 1.1 "Query Language" component. Specifically, the class of queries we consider consists of sets of SPARQL triple patterns with labeled property paths. From a relational perspective, this class resolves to conjunctive queries of relational joins with additional graph-reachability predicates. For the scalable, i.e., distributed, processing of this kind of queries over very large RDF collections, we develop a suitable partitioning and indexing scheme, which allows us to shard the RDF triples over an entire cluster of compute nodes and to process an incoming SPARQL query over all of the relevant graph partitions (and thus compute nodes) in parallel. Unlike most prior works in this field, we specifically aim at the unified optimization and distributed processing of queries consisting of both relational joins and graph-reachability predicates. All communication among the compute nodes is established via a proprietary, asynchronous communication protocol based on the Message Passing Interface. %K Computer Science, Databases, cs.DB
[35]
S. Gurajada and M. Theobald, “Distributed Set Reachability,” in SIGMOD’16, ACM SIGMOD International Conference on Management of Data, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{GurajadaSIGMOD2016, TITLE = {Distributed Set Reachability}, AUTHOR = {Gurajada, Sairam and Theobald, Martin}, LANGUAGE = {eng}, ISBN = {978-1-4503-3531-7}, DOI = {10.1145/2882903.2915226}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {SIGMOD'16, ACM SIGMOD International Conference on Management of Data}, PAGES = {1247--1261}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Gurajada, Sairam %A Theobald, Martin %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Distributed Set Reachability : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-220F-5 %R 10.1145/2882903.2915226 %D 2016 %B ACM SIGMOD International Conference on Management of Data %Z date of event: 2016-06-26 - 2016-07-01 %C San Francisco, CA, USA %B SIGMOD'16 %P 1247 - 1261 %I ACM %@ 978-1-4503-3531-7
[36]
M. Halbe, “Skim: Alternative Candidate Selections for Slim through Sketching,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{HalbeBcS2016, TITLE = {Skim: Alternative Candidate Selections for Slim through Sketching}, AUTHOR = {Halbe, Magnus}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, TYPE = {Bachelor's thesis}, }
Endnote
%0 Thesis %A Halbe, Magnus %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Skim: Alternative Candidate Selections for Slim through Sketching : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F44-6 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P X, 52 p. %V bachelor %9 bachelor
[37]
Y. He, K. Chakrabarti, T. Cheng, and T. Tylenda, “Automatic Discovery of Attribute Synonyms Using Query Logs and Table Corpora,” in WWW’16, 25th International Conference on World Wide Web, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{He_WWW2016, TITLE = {Automatic Discovery of Attribute Synonyms Using Query Logs and Table Corpora}, AUTHOR = {He, Yeye and Chakrabarti, Kaushik and Cheng, Tao and Tylenda, Tomasz}, LANGUAGE = {eng}, ISBN = {978-1-4503-4143-1}, DOI = {10.1145/2872427.2874816}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16, 25th International Conference on World Wide Web}, PAGES = {1429--1439}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A He, Yeye %A Chakrabarti, Kaushik %A Cheng, Tao %A Tylenda, Tomasz %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Automatic Discovery of Attribute Synonyms Using Query Logs and Table Corpora : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-312D-5 %R 10.1145/2872427.2874816 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 %P 1429 - 1439 %I ACM %@ 978-1-4503-4143-1
[38]
J. Hoffart, D. Milchevski, G. Weikum, A. Anand, and J. Singh, “The Knowledge Awakens: Keeping Knowledge Bases Fresh with Emerging Entities,” in WWW’16 Companion, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{HoffartWWW2016, TITLE = {The Knowledge Awakens: {K}eeping Knowledge Bases Fresh with Emerging Entities}, AUTHOR = {Hoffart, Johannes and Milchevski, Dragan and Weikum, Gerhard and Anand, Avishek and Singh, Jaspreet}, LANGUAGE = {eng}, ISBN = {978-1-4503-4144-8}, DOI = {10.1145/2872518.2890537}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16 Companion}, PAGES = {203--206}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Hoffart, Johannes %A Milchevski, Dragan %A Weikum, Gerhard %A Anand, Avishek %A Singh, Jaspreet %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T The Knowledge Awakens: Keeping Knowledge Bases Fresh with Emerging Entities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-01BB-4 %R 10.1145/2872518.2890537 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 Companion %P 203 - 206 %I ACM %@ 978-1-4503-4144-8
[39]
K. Hui and K. Berberich, “Cluster Hypothesis in Low-Cost IR Evaluation with Different Document Representations,” in WWW’16 Companion, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{HuiWWW2016, TITLE = {Cluster Hypothesis in Low-Cost {IR} Evaluation with Different Document Representations}, AUTHOR = {Hui, Kai and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-1-4503-4144-8}, DOI = {10.1145/2872518.2889370}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16 Companion}, PAGES = {47--48}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Hui, Kai %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Cluster Hypothesis in Low-Cost IR Evaluation with Different Document Representations : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-08E3-C %R 10.1145/2872518.2889370 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 Companion %P 47 - 48 %I ACM %@ 978-1-4503-4144-8
[40]
Y. Ibrahim, M. Riedewald, and G. Weikum, “Making Sense of Entities and Quantities in Web Tables,” in CIKM’16, 25th ACM Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
Export
BibTeX
@inproceedings{Ibrahim:CIKM2016, TITLE = {Making Sense of Entities and Quantities in {Web} Tables}, AUTHOR = {Ibrahim, Yusra and Riedewald, Mirek and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4073-1}, DOI = {10.1145/2983323.2983772}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {CIKM'16, 25th ACM Conference on Information and Knowledge Management}, PAGES = {1703--1712}, ADDRESS = {Indianapolis, IN, USA}, }
Endnote
%0 Conference Proceedings %A Ibrahim, Yusra %A Riedewald, Mirek %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Making Sense of Entities and Quantities in Web Tables : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4852-E %R 10.1145/2983323.2983772 %D 2016 %B 25th ACM Conference on Information and Knowledge Management %Z date of event: 2016-10-24 - 2016-10-28 %C Indianapolis, IN, USA %B CIKM'16 %P 1703 - 1712 %I ACM %@ 978-1-4503-4073-1
[41]
J. Kalofolias, “Maximum Entropy Models for Redescription Mining,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{KalofoliasMSc2016, TITLE = {Maximum Entropy Models for Redescription Mining}, AUTHOR = {Kalofolias, Janis}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Kalofolias, Janis %Y Miettinen, Pauli %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Maximum Entropy Models for Redescription Mining : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-54C0-6 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P III, 51 p. %V master %9 master
[42]
S. Karaev and P. Miettinen, “Cancer: Another Algorithm for Subtropical Matrix Factorization,” in Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016), Riva del Garda, Italy, 2016.
Export
BibTeX
@inproceedings{KaraevECML2016, TITLE = {Cancer: {A}nother Algorithm for Subtropical Matrix Factorization}, AUTHOR = {Karaev, Sanjar and Miettinen, Pauli}, LANGUAGE = {eng}, ISBN = {978-3-319-46226-4}, DOI = {10.1007/978-3-319-46227-1_36}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016)}, EDITOR = {Frasconi, Paolo and Landwehr, Niels and Manco, Guiseppe and Vreeken, Jilles}, PAGES = {576--592}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9852}, ADDRESS = {Riva del Garda, Italy}, }
Endnote
%0 Conference Proceedings %A Karaev, Sanjar %A Miettinen, Pauli %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Cancer: Another Algorithm for Subtropical Matrix Factorization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A926-A %R 10.1007/978-3-319-46227-1_36 %D 2016 %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases %Z date of event: 2016-09-19 - 2016-09-23 %C Riva del Garda, Italy %B Machine Learning and Knowledge Discovery in Databases %E Frasconi, Paolo; Landwehr, Niels; Manco, Guiseppe; Vreeken, Jilles %P 576 - 592 %I Springer %@ 978-3-319-46226-4 %B Lecture Notes in Artificial Intelligence %N 9852
[43]
S. Karaev and P. Miettinen, “Capricorn: An Algorithm for Subtropical Matrix Factorization,” in Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016), Miama, FL, USA, 2016.
Abstract
Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.
Export
BibTeX
@inproceedings{karaev16capricorn, TITLE = {Capricorn: {An} Algorithm for Subtropical Matrix Factorization}, AUTHOR = {Karaev, Sanjar and Miettinen, Pauli}, LANGUAGE = {eng}, ISBN = {978-1-61197-434-8}, DOI = {10.1137/1.9781611974348.79}, PUBLISHER = {SIAM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, ABSTRACT = {Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.}, BOOKTITLE = {Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016)}, EDITOR = {Chawla Venkatasubramanian, Sanjay and Meira, Wagner}, PAGES = {702--710}, ADDRESS = {Miama, FL, USA}, }
Endnote
%0 Conference Proceedings %A Karaev, Sanjar %A Miettinen, Pauli %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Capricorn: An Algorithm for Subtropical Matrix Factorization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-542F-3 %R 10.1137/1.9781611974348.79 %D 2016 %B 16th SIAM International Conference on Data Mining %Z date of event: 2016-05-05 - 2016-05-07 %C Miama, FL, USA %X Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data. %B Proceedings of the Sixteenth SIAM International Conference on Data Mining %E Chawla Venkatasubramanian, Sanjay; Meira, Wagner %P 702 - 710 %I SIAM %@ 978-1-61197-434-8
[44]
M. Krötzsch and G. Weikum, “Editorial,” Journal of Web Semantics, vol. 37/38, 2016.
Export
BibTeX
@article{Kroetzsch2016, TITLE = {Editorial}, AUTHOR = {Kr{\"o}tzsch, Markus and Weikum, Gerhard}, LANGUAGE = {eng}, ISSN = {1570-8268}, DOI = {10.1016/j.websem.2016.04.002}, PUBLISHER = {Elsevier}, ADDRESS = {Amsterdam}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Journal of Web Semantics}, VOLUME = {37/38}, PAGES = {53--54}, }
Endnote
%0 Journal Article %A Krötzsch, Markus %A Weikum, Gerhard %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Editorial : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-EB8D-B %R 10.1016/j.websem.2016.04.002 %7 2016 %D 2016 %J Journal of Web Semantics %O Science, Services and Agents on the World Wide Web Web Semantics: Science, Services and Agents on the World Wide Web %V 37/38 %& 53 %P 53 - 54 %I Elsevier %C Amsterdam %@ false
[45]
E. Kuzey, J. Strötgen, V. Setty, and G. Weikum, “Temponym Tagging: Temporal Scopes for Textual Phrases,” in WWW’16 Companion, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{Kuzey:2016:TTT:2872518.2889289, TITLE = {Temponym Tagging: {T}emporal Scopes for Textual Phrases}, AUTHOR = {Kuzey, Erdal and Str{\"o}tgen, Jannik and Setty, Vinay and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4144-8}, DOI = {10.1145/2872518.2889289}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16 Companion}, PAGES = {841--842}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Kuzey, Erdal %A Strötgen, Jannik %A Setty, Vinay %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Temponym Tagging: Temporal Scopes for Textual Phrases : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-4134-1 %R 10.1145/2872518.2889289 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 Companion %P 841 - 842 %I ACM %@ 978-1-4503-4144-8
[46]
E. Kuzey, V. Setty, J. Strötgen, and G. Weikum, “As Time Goes By: Comprehensive Tagging of Textual Phrases with Temporal Scopes,” in WWW’16, 25th International Conference on World Wide Web, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{Kuzey_WWW2016, TITLE = {As Time Goes By: {C}omprehensive Tagging of Textual Phrases with Temporal Scopes}, AUTHOR = {Kuzey, Erdal and Setty, Vinay and Str{\"o}tgen, Jannik and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4143-1}, DOI = {10.1145/2872427.2883055}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16, 25th International Conference on World Wide Web}, PAGES = {915--925}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Kuzey, Erdal %A Setty, Vinay %A Strötgen, Jannik %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T As Time Goes By: Comprehensive Tagging of Textual Phrases with Temporal Scopes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-310D-D %R 10.1145/2872427.2883055 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 %P 915 - 925 %I ACM %@ 978-1-4503-4143-1
[47]
S. Metzler, S. Günnemann, and P. Miettinen, “Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques,” 2016. [Online]. Available: http://arxiv.org/abs/1602.04650. (arXiv: 1602.04650)
Abstract
Cliques (or quasi-cliques) are frequently used to model communities: a set of nodes where each pair is (equally) likely to be connected. However, when observing real-world communities, we see that most communities have more structure than that. In particular, the nodes can be ordered in such a way that (almost) all edges in the community lie below a hyperbola. In this paper we present three new models for communities that capture this phenomenon. Our models explain the structure of the communities differently, but we also prove that they are identical in their expressive power. Our models fit to real-world data much better than traditional block models, and allow for more in-depth understanding of the structure of the data.
Export
BibTeX
@online{Metzler_arXiv2016, TITLE = {Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques}, AUTHOR = {Metzler, Saskia and G{\"u}nnemann, Stephan and Miettinen, Pauli}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1602.04650}, EPRINT = {1602.04650}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Cliques (or quasi-cliques) are frequently used to model communities: a set of nodes where each pair is (equally) likely to be connected. However, when observing real-world communities, we see that most communities have more structure than that. In particular, the nodes can be ordered in such a way that (almost) all edges in the community lie below a hyperbola. In this paper we present three new models for communities that capture this phenomenon. Our models explain the structure of the communities differently, but we also prove that they are identical in their expressive power. Our models fit to real-world data much better than traditional block models, and allow for more in-depth understanding of the structure of the data.}, }
Endnote
%0 Report %A Metzler, Saskia %A Günnemann, Stephan %A Miettinen, Pauli %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-08E5-8 %U http://arxiv.org/abs/1602.04650 %D 2016 %X Cliques (or quasi-cliques) are frequently used to model communities: a set of nodes where each pair is (equally) likely to be connected. However, when observing real-world communities, we see that most communities have more structure than that. In particular, the nodes can be ordered in such a way that (almost) all edges in the community lie below a hyperbola. In this paper we present three new models for communities that capture this phenomenon. Our models explain the structure of the communities differently, but we also prove that they are identical in their expressive power. Our models fit to real-world data much better than traditional block models, and allow for more in-depth understanding of the structure of the data. %K cs.SI, Physics, Physics and Society, physics.soc-ph
[48]
P. Mirza, S. Razniewski, and W. Nutt, “Expanding Wikidata’s Parenthood Information by 178%, or How To Mine Relation Cardinalities,” in Proceedings of the ISWC 2016 Posters & Demonstrations Track co-located with 15th International Semantic Web Conference (ISWC-P&D 2016), Kobe, Japan, 2016.
Export
BibTeX
@inproceedings{DBLP:conf/semweb/MirzaRN16, TITLE = {Expanding {W}ikidata's Parenthood Information by 178{\%}, or How To Mine Relation Cardinalities}, AUTHOR = {Mirza, Paramita and Razniewski, Simon and Nutt, Werner}, LANGUAGE = {eng}, URL = {urn:nbn:de:0074-1690-5}, PUBLISHER = {CEUR-WS.org}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the ISWC 2016 Posters \& Demonstrations Track co-located with 15th International Semantic Web Conference (ISWC-P\&D 2016)}, EDITOR = {Kawamura, Takahiro and Paulheim, Heiko}, EID = {4}, SERIES = {CEUR Workshop Proceedings}, VOLUME = {1690}, ADDRESS = {Kobe, Japan}, }
Endnote
%0 Conference Proceedings %A Mirza, Paramita %A Razniewski, Simon %A Nutt, Werner %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Expanding Wikidata's Parenthood Information by 178%, or How To Mine Relation Cardinalities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-23C1-9 %D 2016 %B ISWC 2016 Posters & Demonstrations Trac %Z date of event: 2016-10-19 - 2016-10-19 %C Kobe, Japan %B Proceedings of the ISWC 2016 Posters & Demonstrations Track co-located with 15th International Semantic Web Conference %E Kawamura, Takahiro; Paulheim, Heiko %Z sequence number: 4 %I CEUR-WS.org %B CEUR Workshop Proceedings %N 1690
[49]
P. Mirza and S. Tonelli, “CATENA: CAusal and TEmporal relation extraction from NAtural language texts,” in Proceedings of COLING 2016: Technical Papers, Osaka, Japan, 2016.
Export
BibTeX
@inproceedings{mirza-tonelli:2016:COLING1, TITLE = {{CATENA}: {CAusal} and {TEmporal} relation extraction from {NAtural} language texts}, AUTHOR = {Mirza, Paramita and Tonelli, Sara}, LANGUAGE = {eng}, ISBN = {978-4-87974-702-0}, PUBLISHER = {ACL}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of COLING 2016: Technical Papers}, PAGES = {64--75}, ADDRESS = {Osaka, Japan}, }
Endnote
%0 Conference Proceedings %A Mirza, Paramita %A Tonelli, Sara %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T CATENA: CAusal and TEmporal relation extraction from NAtural language texts : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-23B8-0 %D 2016 %B The 26th International Conference on Computational Linguistics %Z date of event: 2016-12-11 - 2016-12-16 %C Osaka, Japan %B Proceedings of COLING 2016: Technical Papers %P 64 - 75 %I ACL %@ 978-4-87974-702-0
[50]
P. Mirza and S. Tonelli, “On the Contribution of Word Embeddings to Temporal Relation Classification,” in Proceedings of COLING 2016: Technical Papers, Osaka, Japan, 2016.
Export
BibTeX
@inproceedings{mirza-tonelli:2016:COLING2, TITLE = {On the Contribution of Word Embeddings to Temporal Relation Classification}, AUTHOR = {Mirza, Paramita and Tonelli, Sara}, LANGUAGE = {eng}, ISBN = {978-4-87974-702-0}, PUBLISHER = {ACL}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of COLING 2016: Technical Papers}, PAGES = {2818--2828}, ADDRESS = {Osaka, Japan}, }
Endnote
%0 Conference Proceedings %A Mirza, Paramita %A Tonelli, Sara %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T On the Contribution of Word Embeddings to Temporal Relation Classification : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-23BB-A %D 2016 %B The 26th International Conference on Computational Linguistics %Z date of event: 2016-12-11 - 2016-12-16 %C Osaka, Japan %B Proceedings of COLING 2016: Technical Papers %P 2818 - 2828 %I ACL %@ 978-4-87974-702-0
[51]
A. Mishra and K. Berberich, “Leveraging Semantic Annotations to Link Wikipedia and News Archives,” Max-Planck-Institut für Informatik, Saarbrücken, MPI-I-2016-5-002, 2016.
Abstract
The incomprehensible amount of information available online has made it difficult to retrospect on past events. We propose a novel linking problem to connect excerpts from Wikipedia summarizing events to online news articles elaborating on them. To address the linking problem, we cast it into an information retrieval task by treating a given excerpt as a user query with the goal to retrieve a ranked list of relevant news articles. We find that Wikipedia excerpts often come with additional semantics, in their textual descriptions, representing the time, geolocations, and named entities involved in the event. Our retrieval model leverages text and semantic annotations as different dimensions of an event by estimating independent query models to rank documents. In our experiments on two datasets, we compare methods that consider different combinations of dimensions and find that the approach that leverages all dimensions suits our problem best.
Export
BibTeX
@techreport{MishraBerberich16, TITLE = {Leveraging Semantic Annotations to Link Wikipedia and News Archives}, AUTHOR = {Mishra, Arunav and Berberich, Klaus}, LANGUAGE = {eng}, ISSN = {0946-011X}, NUMBER = {MPI-I-2016-5-002}, INSTITUTION = {Max-Planck-Institut f{\"u}r Informatik}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {The incomprehensible amount of information available online has made it difficult to retrospect on past events. We propose a novel linking problem to connect excerpts from Wikipedia summarizing events to online news articles elaborating on them. To address the linking problem, we cast it into an information retrieval task by treating a given excerpt as a user query with the goal to retrieve a ranked list of relevant news articles. We find that Wikipedia excerpts often come with additional semantics, in their textual descriptions, representing the time, geolocations, and named entities involved in the event. Our retrieval model leverages text and semantic annotations as different dimensions of an event by estimating independent query models to rank documents. In our experiments on two datasets, we compare methods that consider different combinations of dimensions and find that the approach that leverages all dimensions suits our problem best.}, TYPE = {Research Reports}, }
Endnote
%0 Report %A Mishra, Arunav %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Leveraging Semantic Annotations to Link Wikipedia and News Archives : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-5FF0-A %Y Max-Planck-Institut für Informatik %C Saarbrücken %D 2016 %P 21 p. %X The incomprehensible amount of information available online has made it difficult to retrospect on past events. We propose a novel linking problem to connect excerpts from Wikipedia summarizing events to online news articles elaborating on them. To address the linking problem, we cast it into an information retrieval task by treating a given excerpt as a user query with the goal to retrieve a ranked list of relevant news articles. We find that Wikipedia excerpts often come with additional semantics, in their textual descriptions, representing the time, geolocations, and named entities involved in the event. Our retrieval model leverages text and semantic annotations as different dimensions of an event by estimating independent query models to rank documents. In our experiments on two datasets, we compare methods that consider different combinations of dimensions and find that the approach that leverages all dimensions suits our problem best. %B Research Reports %@ false
[52]
A. Mishra and K. Berberich, “Leveraging Semantic Annotations to Link Wikipedia and News Archives,” in Advances in Information Retrieval (ECIR 2016), Padova, Italy, 2016.
Export
BibTeX
@inproceedings{MishraECIR2016, TITLE = {Leveraging Semantic Annotations to Link {W}ikipedia and News Archives}, AUTHOR = {Mishra, Arunav and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-3-319-30670-4}, DOI = {10.1007/978-3-319-30671-1_3}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Advances in Information Retrieval (ECIR 2016)}, EDITOR = {Ferro, Nicola and Crestani, Fabio and Moens, Marie-Francine and Mothe, Josiane and Silvestre, Fabrizio and Di Nunzio, Giorgio Maria and Hauff, Claudia and Silvello, Gianmaria}, PAGES = {30--42}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9626}, ADDRESS = {Padova, Italy}, }
Endnote
%0 Conference Proceedings %A Mishra, Arunav %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Leveraging Semantic Annotations to Link Wikipedia and News Archives : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-48DC-F %R 10.1007/978-3-319-30671-1_3 %D 2016 %B 38th European Conference on Information Retrieval %Z date of event: 2016-03-20 - 2016-03-23 %C Padova, Italy %B Advances in Information Retrieval %E Ferro, Nicola; Crestani, Fabio; Moens, Marie-Francine; Mothe, Josiane; Silvestre, Fabrizio; Di Nunzio, Giorgio Maria; Hauff, Claudia; Silvello, Gianmaria %P 30 - 42 %I Springer %@ 978-3-319-30670-4 %B Lecture Notes in Computer Science %N 9626
[53]
A. Mishra and K. Berberich, “Estimating Time Models for News Article Excerpts,” in CIKM’16, 25th ACM Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
Export
BibTeX
@inproceedings{DBLP:conf/cikm/MishraB16, TITLE = {Estimating Time Models for News Article Excerpts}, AUTHOR = {Mishra, Arunav and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-1-4503-4073-1}, DOI = {10.1145/2983323.2983802}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {CIKM'16, 25th ACM Conference on Information and Knowledge Management}, PAGES = {781--790}, ADDRESS = {Indianapolis, IN, USA}, }
Endnote
%0 Conference Proceedings %A Mishra, Arunav %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Estimating Time Models for News Article Excerpts : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-20CF-3 %R 10.1145/2983323.2983802 %D 2016 %B 25th ACM Conference on Information and Knowledge Management %Z date of event: 2016-10-24 - 2016-10-28 %C Indianapolis, IN, USA %B CIKM'16 %P 781 - 790 %I ACM %@ 978-1-4503-4073-1
[54]
A. Mishra and K. Berberich, “Event Digest: A Holistic View on Past Events,” in SIGIR’16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Italy, 2016.
Export
BibTeX
@inproceedings{MishraSIGIR2016, TITLE = {Event Digest: {A} Holistic View on Past Events}, AUTHOR = {Mishra, Arunav and Berberich, Klaus}, LANGUAGE = {eng}, ISBN = {978-1-4503-4069-4}, DOI = {10.1145/2911451.2911526}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {SIGIR'16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval}, PAGES = {493--502}, ADDRESS = {Pisa, Italy}, }
Endnote
%0 Conference Proceedings %A Mishra, Arunav %A Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Event Digest: A Holistic View on Past Events : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0895-D %R 10.1145/2911451.2911526 %D 2016 %B 39th International ACM SIGIR Conference on Research and Development in Information Retrieval %Z date of event: 2016-07-17 - 2016-07-21 %C Pisa, Italy %B SIGIR'16 %P 493 - 502 %I ACM %@ 978-1-4503-4069-4
[55]
S. Mukherjee, S. Günnemann, and G. Weikum, “Continuous Experience-aware Language Model,” in KDD’16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{MukherjeeKDD2016, TITLE = {Continuous Experience-aware Language Model}, AUTHOR = {Mukherjee, Subhabrata and G{\"u}nnemann, Stephan and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4232-2}, DOI = {10.1145/2939672.2939780}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {KDD'16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining}, PAGES = {1075--1084}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Mukherjee, Subhabrata %A Günnemann, Stephan %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Continuous Experience-aware Language Model : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A678-6 %R 10.1145/2939672.2939780 %D 2016 %B 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining %Z date of event: 2016-08-13 - 2016-08-17 %C San Francisco, CA, USA %B KDD'16 %P 1075 - 1084 %I ACM %@ 978-1-4503-4232-2
[56]
S. Mukherjee, S. Dutta, and G. Weikum, “Credible Review Detection with Limited Information Using Consistency Features,” in Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016), Riva del Garda, Italy, 2016.
Export
BibTeX
@inproceedings{MukherjeeECML2016, TITLE = {Credible Review Detection with Limited Information Using Consistency Features}, AUTHOR = {Mukherjee, Subhabrata and Dutta, Sourav and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-3-319-46226-4}, DOI = {10.1007/978-3-319-46227-1_13}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2016)}, EDITOR = {Frasconi, Paolo and Landwehr, Niels and Manco, Guiseppe and Vreeken, Jilles}, PAGES = {195--213}, SERIES = {Lecture Notes in Artificial Intelligence}, VOLUME = {9852}, ADDRESS = {Riva del Garda, Italy}, }
Endnote
%0 Conference Proceedings %A Mukherjee, Subhabrata %A Dutta, Sourav %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Credible Review Detection with Limited Information Using Consistency Features : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A67C-D %R 10.1007/978-3-319-46227-1_13 %D 2016 %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases %Z date of event: 2016-09-19 - 2016-09-23 %C Riva del Garda, Italy %B Machine Learning and Knowledge Discovery in Databases %E Frasconi, Paolo; Landwehr, Niels; Manco, Guiseppe; Vreeken, Jilles %P 195 - 213 %I Springer %@ 978-3-319-46226-4 %B Lecture Notes in Artificial Intelligence %N 9852
[57]
N. Mukuze and P. Miettinen, “Interactive Constrained Boolean Matrix Factorization,” in Proceedings of the ACM SIGKDD 2016 Full-day Workshop on Interactive Data Exploration and Analytics (IDEA 2016), San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{mukuze16interactive, TITLE = {Interactive Constrained {B}oolean Matrix Factorization}, AUTHOR = {Mukuze, Nelson and Miettinen, Pauli}, LANGUAGE = {eng}, YEAR = {2015}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the ACM SIGKDD 2016 Full-day Workshop on Interactive Data Exploration and Analytics (IDEA 2016)}, EDITOR = {Chau, Duen Horng and Vreeken, Jilles and van Leeuwen, Matthijs and Shahaf, Dafna and Faloutsos, Christos}, PAGES = {96--104}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Mukuze, Nelson %A Miettinen, Pauli %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Interactive Constrained Boolean Matrix Factorization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-226C-2 %D 2016 %B ACM SIGKDD 2016 Full-day Workshop on Interactive Data Exploration and Analytics %Z date of event: 2015-08-14 - 2014-08-14 %C San Francisco, CA, USA %B Proceedings of the ACM SIGKDD 2016 Full-day Workshop on Interactive Data Exploration and Analytics %E Chau, Duen Horng; Vreeken, Jilles; van Leeuwen, Matthijs; Shahaf, Dafna; Faloutsos , Christos %P 96 - 104
[58]
N. Mukuze, “Interactive Boolean Matrix Factorization,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{MukuzeMSc2016, TITLE = {Interactive Boolean Matrix Factorization}, AUTHOR = {Mukuze, Nelson}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Mukuze, Nelson %Y Miettinen, Pauli %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Interactive Boolean Matrix Factorization : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-54C8-5 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P III, 68 p. %V master %9 master
[59]
S. Nag Chowdhury, “Commonsense for Making Sense of Data,” in Proceedings of the VLDB 2016 PhD Workshop co-located with the 42nd International Conference on Very Large Databases (VLDB 2016), New Delhi, India, 2016.
Export
BibTeX
@inproceedings{NagChowdhuryVLDB2016, TITLE = {Commonsense for Making Sense of Data}, AUTHOR = {Nag Chowdhury, Sreyasi}, LANGUAGE = {eng}, URL = {urn:nbn:de:0074-1671-7; urn:nbn:de:0074-1671-7}, PUBLISHER = {CEUR-WS.org}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the VLDB 2016 PhD Workshop co-located with the 42nd International Conference on Very Large Databases (VLDB 2016)}, EDITOR = {Grust, Torsten and Karlapalem, Kamal and Pavlo, Andyq}, EID = {8}, SERIES = {CEUR Workshop Proceedings}, VOLUME = {1671}, ADDRESS = {New Delhi, India}, }
Endnote
%0 Conference Proceedings %A Nag Chowdhury, Sreyasi %+ Databases and Information Systems, MPI for Informatics, Max Planck Society %T Commonsense for Making Sense of Data : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-22E4-3 %U urn:nbn:de:0074-1671-7 %D 2016 %B VLDB 2016 PhD Workshop %Z date of event: 2016-09-09 - 2016-09-09 %C New Delhi, India %B Proceedings of the VLDB 2016 PhD Workshop co-located with the 42nd International Conference on Very Large Databases (VLDB 2016) %E Grust, Torsten; Karlapalem, Kamal; Pavlo, Andyq %Z sequence number: 8 %I CEUR-WS.org %B CEUR Workshop Proceedings %N 1671
[60]
S. Nag Chowdhury, N. Tandon, and G. Weikum, “Know2Look: Commonsense Knowledge for Visual Search,” in AKBC 2016, 5th Workshop on Automated Knowledge Base Construction, San Diego, CA, USA, 2016.
Export
BibTeX
@inproceedings{DBLP:conf/akbc/ChowdhuryTW16, TITLE = {{Know2Look}: {C}ommonsense Knowledge for Visual Search}, AUTHOR = {Nag Chowdhury, Sreyasi and Tandon, Niket and Weikum, Gerhard}, LANGUAGE = {eng}, URL = {http://www.akbc.ws/2016/papers/11_Paper.pdf}, PUBLISHER = {AKBC Board}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {AKBC 2016, 5th Workshop on Automated Knowledge Base Construction}, PAGES = {57--62}, ADDRESS = {San Diego, CA, USA}, }
Endnote
%0 Conference Proceedings %A Nag Chowdhury, Sreyasi %A Tandon, Niket %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Know2Look: Commonsense Knowledge for Visual Search : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A633-2 %U http://www.akbc.ws/2016/papers/11_Paper.pdf %D 2016 %B 5th Workshop on Automated Knowledge Base Construction %Z date of event: 2016-06-17 - 2016-06-17 %C San Diego, CA, USA %B AKBC 2016 %P 57 - 62 %I AKBC Board
[61]
D. B. Nguyen, M. Theobald, and G. Weikum, “J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features,” Transactions of the Association for Computational Linguistics, vol. 4, 2016.
Export
BibTeX
@article{Nguyen2016, TITLE = {{J}-{NERD}: {J}oint {N}amed {E}ntity {R}ecognition and {D}isambiguation with Rich Linguistic Features}, AUTHOR = {Nguyen, Dat Ba and Theobald, Martin and Weikum, Gerhard}, LANGUAGE = {eng}, ISSN = {2307-387X}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, JOURNAL = {Transactions of the Association for Computational Linguistics}, VOLUME = {4}, PAGES = {215--229}, }
Endnote
%0 Journal Article %A Nguyen, Dat Ba %A Theobald, Martin %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T J-NERD: Joint Named Entity Recognition and Disambiguation with Rich Linguistic Features : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-0199-1 %7 2016 %D 2016 %J Transactions of the Association for Computational Linguistics %O TACL %V 4 %& 215 %P 215 - 229 %@ false %U https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/698
[62]
H.-V. Nguyen and J. Vreeken, “Linear-time Detection of Non-linear Changes in Massively High Dimensional Time Series,” in Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016), Miama, FL, USA, 2016.
Abstract
Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.
Export
BibTeX
@inproceedings{VreekenSDM2016, TITLE = {Linear-time Detection of Non-linear Changes in Massively High Dimensional Time Series}, AUTHOR = {Nguyen, Hoang-Vu and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-1-61197-434-8}, DOI = {10.1137/1.9781611974348.93}, PUBLISHER = {SIAM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, ABSTRACT = {Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.}, BOOKTITLE = {Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016)}, EDITOR = {Chawla Venkatasubramanian, Sanjay and Meira, Wagner}, PAGES = {828--836}, ADDRESS = {Miama, FL, USA}, }
Endnote
%0 Conference Proceedings %A Nguyen, Hoang-Vu %A Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Linear-time Detection of Non-linear Changes in Massively High Dimensional Time Series : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A937-4 %R 10.1137/1.9781611974348.93 %D 2016 %B 16th SIAM International Conference on Data Mining %Z date of event: 2016-05-05 - 2016-05-07 %C Miama, FL, USA %X Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data. %B Proceedings of the Sixteenth SIAM International Conference on Data Mining %E Chawla Venkatasubramanian, Sanjay; Meira, Wagner %P 828 - 836 %I SIAM %@ 978-1-61197-434-8
[63]
H.-V. Nguyen and J. Vreeken, “Flexibly Mining Better Subgroups,” in Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016), Miama, FL, USA, 2016.
Abstract
Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.
Export
BibTeX
@inproceedings{NguyenSDM2016, TITLE = {Flexibly Mining Better Subgroups}, AUTHOR = {Nguyen, Hoang-Vu and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-1-61197-434-8}, DOI = {10.1137/1.9781611974348.66}, PUBLISHER = {SIAM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, ABSTRACT = {Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.}, BOOKTITLE = {Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016)}, EDITOR = {Chawla Venkatasubramanian, Sanjay and Meira, Wagner}, PAGES = {585--593}, ADDRESS = {Miama, FL, USA}, }
Endnote
%0 Conference Proceedings %A Nguyen, Hoang-Vu %A Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Flexibly Mining Better Subgroups : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A933-C %R 10.1137/1.9781611974348.66 %D 2016 %B 16th SIAM International Conference on Data Mining %Z date of event: 2016-05-05 - 2016-05-07 %C Miama, FL, USA %X Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data. %B Proceedings of the Sixteenth SIAM International Conference on Data Mining %E Chawla Venkatasubramanian, Sanjay; Meira, Wagner %P 585 - 593 %I SIAM %@ 978-1-61197-434-8
[64]
H.-V. Nguyen, P. Mandros, and J. Vreeken, “Universal Dependency Analysis,” in Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016), Miama, FL, USA, 2016.
Abstract
Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.
Export
BibTeX
@inproceedings{MandrosSDM2016, TITLE = {Universal Dependency Analysis}, AUTHOR = {Nguyen, Hoang-Vu and Mandros, Panagiotis and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-1-61197-434-8}, DOI = {10.1137/1.9781611974348.89}, PUBLISHER = {SIAM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, ABSTRACT = {Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data.}, BOOKTITLE = {Proceedings of the Sixteenth SIAM International Conference on Data Mining (SDM 2016)}, EDITOR = {Chawla Venkatasubramanian, Sanjay and Meira, Wagner}, PAGES = {792--800}, ADDRESS = {Miama, FL, USA}, }
Endnote
%0 Conference Proceedings %A Nguyen, Hoang-Vu %A Mandros, Panagiotis %A Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Universal Dependency Analysis : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A935-8 %R 10.1137/1.9781611974348.89 %D 2016 %B 16th SIAM International Conference on Data Mining %Z date of event: 2016-05-05 - 2016-05-07 %C Miama, FL, USA %X Finding patterns from binary data is a classical problem in data mining, dating back to at least frequent itemset mining. More recently, approaches such as tiling and Boolean matrix factorization (BMF), have been proposed to find sets of patterns that aim to explain the full data well. These methods, however, are not robust against non-trivial destructive noise, i.e. when relatively many 1s are removed from the data: tiling can only model additive noise while BMF assumes approximately equal amounts of additive and destructive noise. Most real-world binary datasets, however, exhibit mostly destructive noise. In presence/absence data, for instance, it is much more common to fail to observe something than it is to observe a spurious presence. To address this problem, we take the recent approach of employing the Minimum Description Length (MDL) principle for BMF and introduce a new algorithm, Nassau, that directly optimizes the description length of the factorization instead of the reconstruction error. In addition, unlike the previous algorithms, it can adjust the factors it has discovered during its search. Empirical evaluation on synthetic data shows that Nassau excels at datasets with high destructive noise levels and its performance on real-world datasets confirms our hypothesis of the high numbers of missing observations in the real-world data. %B Proceedings of the Sixteenth SIAM International Conference on Data Mining %E Chawla Venkatasubramanian, Sanjay; Meira, Wagner %P 792 - 800 %I SIAM %@ 978-1-61197-434-8
[65]
K. Popat, S. Mukherjee, J. Strötgen, and G. Weikum, “Credibility Assessment of Textual Claims on the Web,” in CIKM’16, 25th ACM International Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
Export
BibTeX
@inproceedings{PopatCIKM2016, TITLE = {Credibility Assessment of Textual Claims on the {Web}}, AUTHOR = {Popat, Kashyap and Mukherjee, Subhabrata and Str{\"o}tgen, Jannik and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4073-1}, DOI = {10.1145/2983323.2983661}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {CIKM'16, 25th ACM International Conference on Information and Knowledge Management}, PAGES = {2173--2178}, ADDRESS = {Indianapolis, IN, USA}, }
Endnote
%0 Conference Proceedings %A Popat, Kashyap %A Mukherjee, Subhabrata %A Strötgen, Jannik %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Credibility Assessment of Textual Claims on the Web : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-B260-3 %R 10.1145/2983323.2983661 %D 2016 %B 25th ACM International Conference on Information and Knowledge Management %Z date of event: 2016-10-24 - 2016-10-28 %C Indianapolis, IN, USA %B CIKM'16 %P 2173 - 2178 %I ACM %@ 978-1-4503-4073-1
[66]
T. Rebele, F. Suchanek, J. Hoffart, J. Biega, E. Kuzey, and G. Weikum, “YAGO: A Multilingual Knowledge Base from Wikipedia, Wordnet, and Geonames,” in The Semantic Web -- ISWC 2016, Kobe, Japan, 2016.
Export
BibTeX
@inproceedings{RebeleISWC2016, TITLE = {{YAGO}: A Multilingual Knowledge Base from {W}ikipedia, {W}ordnet, and {G}eonames}, AUTHOR = {Rebele, Thomas and Suchanek, Fabian and Hoffart, Johannes and Biega, Joanna and Kuzey, Erdal and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-3-319-46546-3}, DOI = {10.1007/978-3-319-46547-0_19}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {The Semantic Web -- ISWC 2016}, EDITOR = {Groth, Paul and Simperl, Elena and Gray, Alasdair and Sabou, Marta and Kr{\"o}tzsch, Markus and Lecue, Freddy and Fl{\"o}ck, Fabian and Gil, Yolanda}, PAGES = {177--185}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9982}, ADDRESS = {Kobe, Japan}, }
Endnote
%0 Conference Proceedings %A Rebele, Thomas %A Suchanek, Fabian %A Hoffart, Johannes %A Biega, Joanna %A Kuzey, Erdal %A Weikum, Gerhard %+ Télécom ParisTech Télécom ParisTech Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T YAGO: A Multilingual Knowledge Base from Wikipedia, Wordnet, and Geonames : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A69A-9 %R 10.1007/978-3-319-46547-0_19 %D 2016 %B 15th International Semantic Web Conference %Z date of event: 2016-10-17 - 2016-10-21 %C Kobe, Japan %B The Semantic Web -- ISWC 2016 %E Groth, Paul; Simperl, Elena; Gray, Alasdair; Sabou, Marta; Krötzsch, Markus; Lecue, Freddy; Flöck, Fabian; Gil, Yolanda %P 177 - 185 %I Springer %@ 978-3-319-46546-3 %B Lecture Notes in Computer Science %N 9982
[67]
R. S. Roy, S. Agarwal, N. Ganguly, and M. Choudhury, “Syntactic Complexity of Web Search Queries through the Lenses of Language Models, Networks and Users,” Information Processing and Management, vol. 52, no. 5, 2016.
Export
BibTeX
@article{Roy2016, TITLE = {Syntactic complexity of {W}eb search queries through the lenses of language models, networks and users}, AUTHOR = {Roy, Rishiraj Saha and Agarwal, Smith and Ganguly, Niloy and Choudhury, Monojit}, LANGUAGE = {eng}, ISSN = {0306-4573}, DOI = {10.1016/j.ipm.2016.04.002}, PUBLISHER = {Elsevier}, ADDRESS = {Amsterdam}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Information Processing and Management}, VOLUME = {52}, NUMBER = {5}, PAGES = {923--948}, }
Endnote
%0 Journal Article %A Roy, Rishiraj Saha %A Agarwal, Smith %A Ganguly, Niloy %A Choudhury, Monojit %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Syntactic Complexity of Web Search Queries through the Lenses of Language Models, Networks and Users : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-7EBE-B %R 10.1016/j.ipm.2016.04.002 %7 2016 %D 2016 %J Information Processing and Management %V 52 %N 5 %& 923 %P 923 - 948 %I Elsevier %C Amsterdam %@ false
[68]
R. S. Roy, A. Suresh, N. Ganguly, and M. Choudhury, “Improving Document Ranking for Long Queries with Nested Query Segmentation,” in Advances in Information Retrieval (ECIR 2016), Padova, Italy, 2016.
Export
BibTeX
@inproceedings{RoyECIR2016, TITLE = {Improving Document Ranking for Long Queries with Nested Query Segmentation}, AUTHOR = {Roy, Rishiraj Saha and Suresh, Anusha and Ganguly, Niloy and Choudhury, Monojit}, LANGUAGE = {eng}, ISBN = {978-3-319-30670-4}, DOI = {10.1007/978-3-319-30671-1_67}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Advances in Information Retrieval (ECIR 2016)}, EDITOR = {Ferro, Nicola and Crestani, Fabio and Moens, Marie-Francine and Mothe, Josiane and Silvestre, Fabrizio and Di Nunzio, Giorgio Maria and Hauff, Claudia and Silvello, Gianmaria}, PAGES = {775--781}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9626}, ADDRESS = {Padova, Italy}, }
Endnote
%0 Conference Proceedings %A Roy, Rishiraj Saha %A Suresh, Anusha %A Ganguly, Niloy %A Choudhury, Monojit %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Improving Document Ranking for Long Queries with Nested Query Segmentation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-48DF-9 %R 10.1007/978-3-319-30671-1_67 %D 2016 %B 38th European Conference on Information Retrieval %Z date of event: 2016-03-20 - 2016-03-23 %C Padova, Italy %B Advances in Information Retrieval %E Ferro, Nicola; Crestani, Fabio; Moens, Marie-Francine; Mothe, Josiane; Silvestre, Fabrizio; Di Nunzio, Giorgio Maria; Hauff, Claudia; Silvello, Gianmaria %P 775 - 781 %I Springer %@ 978-3-319-30670-4 %B Lecture Notes in Computer Science %N 9626
[69]
P. Rozenshtein, A. Gionis, B. A. Prakash, and J. Vreeken, “Reconstructing an Epidemic Over Time,” in KDD’16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{RozenshteinKDD2016, TITLE = {Reconstructing an Epidemic Over Time}, AUTHOR = {Rozenshtein, Polina and Gionis, Aristides and Prakash, B. Aditya and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-1-4503-4232-2}, DOI = {10.1145/2939672.2939865}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {KDD'16, 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining}, PAGES = {1835 --1844}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Rozenshtein, Polina %A Gionis, Aristides %A Prakash, B. Aditya %A Vreeken, Jilles %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Reconstructing an Epidemic Over Time : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A92F-7 %R 10.1145/2939672.2939865 %D 2016 %B 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining %Z date of event: 2016-08-13 - 2016-08-17 %C San Francisco, CA, USA %B KDD'16 %P 1835 - 1844 %I ACM %@ 978-1-4503-4232-2
[70]
M. Salyaeva, “Summarising and Recommending with Skipisodes,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{SalyaevaMSc2016, TITLE = {Summarising and Recommending with Skipisodes}, AUTHOR = {Salyaeva, Margarita}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Salyaeva, Margarita %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Summarising and Recommending with Skipisodes : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F46-2 %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master
[71]
A. Schmidt, J. Hoffart, D. Milchevski, and G. Weikum, “Context-Sensitive Auto-Completion for Searching with Entities and Categories,” in SIGIR’16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Italy, 2016.
Export
BibTeX
@inproceedings{SchmidtIGIR2016, TITLE = {Context-Sensitive Auto-Completion for Searching with Entities and Categories}, AUTHOR = {Schmidt, Andreas and Hoffart, Johannes and Milchevski, Dragan and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4069-4}, DOI = {10.1145/2911451.2911461}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {SIGIR'16, 39th International ACM SIGIR Conference on Research and Development in Information Retrieval}, PAGES = {1097--1100}, ADDRESS = {Pisa, Italy}, }
Endnote
%0 Conference Proceedings %A Schmidt, Andreas %A Hoffart, Johannes %A Milchevski, Dragan %A Weikum, Gerhard %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Context-Sensitive Auto-Completion for Searching with Entities and Categories : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A924-E %R 10.1145/2911451.2911461 %D 2016 %B 39th International ACM SIGIR Conference on Research and Development in Information Retrieval %Z date of event: 2016-07-17 - 2016-07-21 %C Pisa, Italy %B SIGIR'16 %P 1097 - 1100 %I ACM %@ 978-1-4503-4069-4
[72]
S. Seufert, P. Ernst, S. J. Bedathur, S. K. Kondreddi, K. Berberich, and G. Weikum, “Instant Espresso: Interactive Analysis of Relationships in Knowledge Graphs,” in WWW’16 Companion, Montréal, Canada, 2016.
Export
BibTeX
@inproceedings{SeufertWWW2016, TITLE = {Instant {E}spresso: {I}nteractive Analysis of Relationships in Knowledge Graphs}, AUTHOR = {Seufert, Stephan and Ernst, Patrick and Bedathur, Srikanta J. and Kondreddi, Sarath Kumar and Berberich, Klaus and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4144-8}, DOI = {10.1145/2872518.2890528}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WWW'16 Companion}, PAGES = {251--254}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Seufert, Stephan %A Ernst, Patrick %A Bedathur, Srikanta J. %A Kondreddi, Sarath Kumar %A Berberich, Klaus %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Instant Espresso: Interactive Analysis of Relationships in Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-01BD-F %R 10.1145/2872518.2890528 %D 2016 %B 25th International Conference on World Wide Web %Z date of event: 2016-05-11 - 2016-05-15 %C Montréal, Canada %B WWW'16 Companion %P 251 - 254 %I ACM %@ 978-1-4503-4144-8
[73]
S. Seufert, K. Berberich, S. J. Bedathur, S. K. Kondreddi, P. Ernst, and G. Weikum, “ESPRESSO: Explaining Relationships between Entity Sets,” in CIKM’16, 25th ACM Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
Export
BibTeX
@inproceedings{DBLP:conf/cikm/SeufertBBKEW16, TITLE = {{ESPRESSO}: {E}xplaining Relationships between Entity Sets}, AUTHOR = {Seufert, Stephan and Berberich, Klaus and Bedathur, Srikanta J. and Kondreddi, Sarath Kumar and Ernst, Patrick and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-4073-1}, DOI = {10.1145/2983323.2983778}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {CIKM'16, 25th ACM Conference on Information and Knowledge Management}, PAGES = {1311--1320}, ADDRESS = {Indianapolis, IN, USA}, }
Endnote
%0 Conference Proceedings %A Seufert, Stephan %A Berberich, Klaus %A Bedathur, Srikanta J. %A Kondreddi, Sarath Kumar %A Ernst, Patrick %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T ESPRESSO: Explaining Relationships between Entity Sets : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-20D3-8 %R 10.1145/2983323.2983778 %D 2016 %B 25th ACM Conference on Information and Knowledge Management %Z date of event: 2016-10-24 - 2016-10-28 %C Indianapolis, IN, USA %B CIKM'16 %P 1311 - 1320 %I ACM %@ 978-1-4503-4073-1
[74]
D. Seyler, M. Yahya, K. Berberich, and O. Alonso, “Automated Question Generation for Quality Control in Human Computation Tasks,” in WebSci’16, ACM Web Science Conference, Hannover, Germany, 2016.
Export
BibTeX
@inproceedings{SeylerWebSci2016, TITLE = {Automated Question Generation for Quality Control in Human Computation Tasks}, AUTHOR = {Seyler, Dominic and Yahya, Mohamed and Berberich, Klaus and Alonso, Omar}, LANGUAGE = {eng}, ISBN = {978-1-4503-4208-7}, DOI = {10.1145/2908131.2908210}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WebSci'16, ACM Web Science Conference}, PAGES = {360--362}, ADDRESS = {Hannover, Germany}, }
Endnote
%0 Conference Proceedings %A Seyler, Dominic %A Yahya, Mohamed %A Berberich, Klaus %A Alonso, Omar %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Automated Question Generation for Quality Control in Human Computation Tasks : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-08DF-7 %R 10.1145/2908131.2908210 %D 2016 %B ACM Web Science Conference %Z date of event: 2016-05-22 - 2016-05-25 %C Hannover, Germany %B WebSci'16 %P 360 - 362 %I ACM %@ 978-1-4503-4208-7
[75]
D. Seyler, M. Yahya, and K. Berberich, “Knowledge Questions from Knowledge Graphs,” 2016. [Online]. Available: http://arxiv.org/abs/1610.09935. (arXiv: 1610.09935)
Abstract
We address the novel problem of automatically generating quiz-style knowledge questions from a knowledge graph such as DBpedia. Questions of this kind have ample applications, for instance, to educate users about or to evaluate their knowledge in a specific domain. To solve the problem, we propose an end-to-end approach. The approach first selects a named entity from the knowledge graph as an answer. It then generates a structured triple-pattern query, which yields the answer as its sole result. If a multiple-choice question is desired, the approach selects alternative answer options. Finally, our approach uses a template-based method to verbalize the structured query and yield a natural language question. A key challenge is estimating how difficult the generated question is to human users. To do this, we make use of historical data from the Jeopardy! quiz show and a semantically annotated Web-scale document collection, engineer suitable features, and train a logistic regression classifier to predict question difficulty. Experiments demonstrate the viability of our overall approach.
Export
BibTeX
@online{Seyler1610.09935, TITLE = {Knowledge Questions from Knowledge Graphs}, AUTHOR = {Seyler, Dominic and Yahya, Mohamed and Berberich, Klaus}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1610.09935}, EPRINT = {1610.09935}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {We address the novel problem of automatically generating quiz-style knowledge questions from a knowledge graph such as DBpedia. Questions of this kind have ample applications, for instance, to educate users about or to evaluate their knowledge in a specific domain. To solve the problem, we propose an end-to-end approach. The approach first selects a named entity from the knowledge graph as an answer. It then generates a structured triple-pattern query, which yields the answer as its sole result. If a multiple-choice question is desired, the approach selects alternative answer options. Finally, our approach uses a template-based method to verbalize the structured query and yield a natural language question. A key challenge is estimating how difficult the generated question is to human users. To do this, we make use of historical data from the Jeopardy! quiz show and a semantically annotated Web-scale document collection, engineer suitable features, and train a logistic regression classifier to predict question difficulty. Experiments demonstrate the viability of our overall approach.}, }
Endnote
%0 Report %A Seyler, Dominic %A Yahya, Mohamed %A Berberich, Klaus %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Knowledge Questions from Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1CB5-F %U http://arxiv.org/abs/1610.09935 %D 2016 %X We address the novel problem of automatically generating quiz-style knowledge questions from a knowledge graph such as DBpedia. Questions of this kind have ample applications, for instance, to educate users about or to evaluate their knowledge in a specific domain. To solve the problem, we propose an end-to-end approach. The approach first selects a named entity from the knowledge graph as an answer. It then generates a structured triple-pattern query, which yields the answer as its sole result. If a multiple-choice question is desired, the approach selects alternative answer options. Finally, our approach uses a template-based method to verbalize the structured query and yield a natural language question. A key challenge is estimating how difficult the generated question is to human users. To do this, we make use of historical data from the Jeopardy! quiz show and a semantically annotated Web-scale document collection, engineer suitable features, and train a logistic regression classifier to predict question difficulty. Experiments demonstrate the viability of our overall approach. %K Computer Science, Computation and Language, cs.CL
[76]
A. Shah, “Recognizing Visual Activities,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{ShahMSc2016, TITLE = {Recognizing Visual Activities}, AUTHOR = {Shah, Ali}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Shah, Ali %Y Weikum, Gerhard %A referee: Berberich, Klaus %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Recognizing Visual Activities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-439D-1 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P 56 p. %V master %9 master
[77]
J. Singh, J. Hoffart, and A. Anand, “Discovering Entities with Just a Little Help from You,” in CIKM’16, 25th ACM Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
Export
BibTeX
@inproceedings{Singh:2016:DEJ:2983323.2983798, TITLE = {Discovering Entities with Just a Little Help from You}, AUTHOR = {Singh, Jaspreet and Hoffart, Johannes and Anand, Avishek}, LANGUAGE = {eng}, ISBN = {978-1-4503-4073-1}, DOI = {10.1145/2983323.2983798}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {CIKM'16, 25th ACM Conference on Information and Knowledge Management}, PAGES = {1331--1340}, ADDRESS = {Indianapolis, IN, USA}, }
Endnote
%0 Conference Proceedings %A Singh, Jaspreet %A Hoffart, Johannes %A Anand, Avishek %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Discovering Entities with Just a Little Help from You : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1CC2-2 %R 10.1145/2983323.2983798 %D 2016 %B 25th ACM Conference on Information and Knowledge Management %Z date of event: 2016-10-24 - 2016-10-28 %C Indianapolis, IN, USA %B CIKM'16 %P 1331 - 1340 %I ACM %@ 978-1-4503-4073-1
[78]
A. Siu, P. Ernst, and G. Weikum, “Disambiguation of Entities in MEDLINE Abstracts by Combining MeSH Terms with Knowledge,” in Proceedings of the 15th Workshop on Biomedical Natural Language Processing (BioNLP 2016), Berlin, Germany, 2016.
Export
BibTeX
@inproceedings{Siu16, TITLE = {Disambiguation of entities in {MEDLINE} abstracts by combining {MeSH} terms with knowledge}, AUTHOR = {Siu, Amy and Ernst, Patrick and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-945626-12-8}, PUBLISHER = {ACL}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Proceedings of the 15th Workshop on Biomedical Natural Language Processing (BioNLP 2016)}, PAGES = {72--76}, ADDRESS = {Berlin, Germany}, }
Endnote
%0 Conference Proceedings %A Siu, Amy %A Ernst, Patrick %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Disambiguation of Entities in MEDLINE Abstracts by Combining MeSH Terms with Knowledge : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2040-3 %D 2016 %B 15th Workshop on Biomedical Natural Language Processing %Z date of event: 2016-08-12 - 2016-08-12 %C Berlin, Germany %B Proceedings of the 15th Workshop on Biomedical Natural Language Processing %P 72 - 76 %I ACL %@ 978-1-945626-12-8 %U http://aclweb.org/anthology/W/W16/W16-2909.pdf
[79]
D. Spanier, “An Incremental Approach to Distilling Named Events from News Streams,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{SpanierMSc2016, TITLE = {An Incremental Approach to Distilling Named Events from News Streams}, AUTHOR = {Spanier, Daniel}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Spanier, Daniel %Y Weikum, Gerhard %A referee: Setty, Vinay %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T An Incremental Approach to Distilling Named Events from News Streams : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4913-0 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P XI, 58 p. %V master %9 master
[80]
J. Strötgen and M. Gertz, Domain-Sensitive Temporal Tagging. San Rafael, CA: Morgan & Claypool Publishers, 2016.
Export
BibTeX
@book{StroetgenBook2016, TITLE = {Domain-Sensitive Temporal Tagging}, AUTHOR = {Str{\"o}tgen, Jannik and Gertz, Michael}, LANGUAGE = {eng}, ISSN = {1947-4040}, ISBN = {9781627054591; 9781627054997}, DOI = {10.2200/S00721ED1V01Y201606HLT036}, PUBLISHER = {Morgan \& Claypool Publishers}, ADDRESS = {San Rafael, CA}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, PAGES = {151 p.}, SERIES = {Synthesis Lectures on Human Language Technologies}, }
Endnote
%0 Book %A Strötgen, Jannik %A Gertz, Michael %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Domain-Sensitive Temporal Tagging : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-1777-9 %@ 9781627054591 %@ 9781627054997 %R 10.2200/S00721ED1V01Y201606HLT036 %I Morgan & Claypool Publishers %C San Rafael, CA %D 2016 %P 151 p. %B Synthesis Lectures on Human Language Technologies %@ false
[81]
J. Strötgen, “Domänen-sensitives Temporal Tagging für Event-zentriertes Information Retrieval,” in Ausgezeichnete Informatikdissertationen 2015, Bonn: GI, 2016.
Export
BibTeX
@incollection{StrotgenLNI_Diss16, TITLE = {{Dom{\"a}nen-sensitives Temporal Tagging f{\"u}r Event-zentriertes Information Retrieval}}, AUTHOR = {Str{\"o}tgen, Jannik}, LANGUAGE = {deu}, ISBN = {978-3-88579-975-7}, PUBLISHER = {GI}, ADDRESS = {Bonn}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Ausgezeichnete Informatikdissertationen 2015}, EDITOR = {H{\"o}lldobler, Steffen}, PAGES = {279--288}, SERIES = {Lecture Notes in Informatics -- Dissertations}, VOLUME = {16}, }
Endnote
%0 Book Section %A Strötgen, Jannik %+ Databases and Information Systems, MPI for Informatics, Max Planck Society %T Domänen-sensitives Temporal Tagging für Event-zentriertes Information Retrieval : %G deu %U http://hdl.handle.net/11858/00-001M-0000-002B-B26A-F %D 2016 %B Ausgezeichnete Informatikdissertationen 2015 %E Hölldobler, Steffen %P 279 - 288 %I GI %C Bonn %@ 978-3-88579-975-7 %S Lecture Notes in Informatics - Dissertations %N 16
[82]
A. Talaika, J. Biega, A. Amarilli, and F. M. Suchanek, “IBEX: Harvesting Entities from the Web Using Unique Identifiers,” in Proceedings of the 18th International Workshop on Web and Databases (WebDB 2015), Melbourne, Australia, 2016.
Export
BibTeX
@inproceedings{Talaika2016, TITLE = {{IBEX}: {H}arvesting Entities from the {Web} Using Unique Identifiers}, AUTHOR = {Talaika, Aliaksandr and Biega, Joanna and Amarilli, Antoine and Suchanek, Fabian M.}, LANGUAGE = {eng}, ISBN = {978-1-4503-3627-7}, DOI = {10.1145/2767109.2767116}, PUBLISHER = {ACM}, YEAR = {2015}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Proceedings of the 18th International Workshop on Web and Databases (WebDB 2015)}, EDITOR = {Stoyanovich, Julia and Suchanek, Fabian M.}, PAGES = {13--19}, ADDRESS = {Melbourne, Australia}, }
Endnote
%0 Conference Proceedings %A Talaika, Aliaksandr %A Biega, Joanna %A Amarilli, Antoine %A Suchanek, Fabian M. %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Télécom ParisTech Télécom ParisTech %T IBEX: Harvesting Entities from the Web Using Unique Identifiers : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-AF0D-5 %R 10.1145/2767109.2767116 %D 2016 %B 18th International Workshop on the Web and Databases %Z date of event: 2015-05-31 - 2015-05-31 %C Melbourne, Australia %B Proceedings of the 18th International Workshop on Web and Databases %E Stoyanovich, Julia; Suchanek, Fabian M. %P 13 - 19 %I ACM %@ 978-1-4503-3627-7
[83]
N. Tandon, C. D. Hariman, J. Urbani, A. Rohrbach, M. Rohrbach, and G. Weikum, “Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags,” in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, 2016.
Export
BibTeX
@inproceedings{TandonAAAI2016, TITLE = {Commonsense in Parts: Mining Part-Whole Relations from the {Web} and Image Tags}, AUTHOR = {Tandon, Niket and Hariman, Charles Darwis and Urbani, Jacopo and Rohrbach, Anna and Rohrbach, Marcus and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-57735-760-5}, PUBLISHER = {AAAI Press}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence}, PAGES = {243--250}, ADDRESS = {Phoenix, AZ, USA}, }
Endnote
%0 Conference Proceedings %A Tandon, Niket %A Hariman, Charles Darwis %A Urbani, Jacopo %A Rohrbach, Anna %A Rohrbach, Marcus %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-ABFE-1 %D 2016 %B Thirtieth AAAI Conference on Artificial Intelligence %Z date of event: 2016-02-12 - 2016-02-17 %C Phoenix, AZ, USA %B Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence %P 243 - 250 %I AAAI Press %@ 978-1-57735-760-5 %U http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12337/11590
[84]
N. Tandon, “Commonsense Knowledge Acquisition and Applications,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@phdthesis{TandonPhD2016, TITLE = {Commonsense Knowledge Acquisition and Applications}, AUTHOR = {Tandon, Niket}, LANGUAGE = {eng}, URL = {urn:nbn:de:bsz:291-scidok-66291}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Tandon, Niket %Y Weikum, Gerhard %A referee: Lieberman, Henry %A referee: Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society International Max Planck Research School, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Commonsense Knowledge Acquisition and Applications : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-78F6-A %U urn:nbn:de:bsz:291-scidok-66291 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P XIV, 154 p. %V phd %9 phd %U http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=dehttp://scidok.sulb.uni-saarland.de/volltexte/2016/6629/
[85]
C. Teflioudi, “Algorithms for Shared-Memory Matrix Completion and Maximum Inner Product Search,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@phdthesis{Teflioudiphd2016, TITLE = {Algorithms for Shared-Memory Matrix Completion and Maximum Inner Product Search}, AUTHOR = {Teflioudi, Christina}, LANGUAGE = {eng}, URL = {urn:nbn:de:bsz:291-scidok-64699}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Teflioudi, Christina %Y Gemulla, Rainer %A referee: Weikum, Gerhard %+ International Max Planck Research School, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Algorithms for Shared-Memory Matrix Completion and Maximum Inner Product Search : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-43FA-2 %U urn:nbn:de:bsz:291-scidok-64699 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P xi, 110 p. %V phd %9 phd %U http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=dehttp://scidok.sulb.uni-saarland.de/volltexte/2016/6469/
[86]
H. D. Tran, D. Stepanova, M. Gad-Elrab, F. A. Lisi, and G. Weikum, “Towards Nonmonotonic Relational Learning from Knowledge Graphs,” in 26th International Conference on Inductive Logic Programming (ILP 2016), London, UK. (Accepted/in press)
Export
BibTeX
@inproceedings{TranILP2016, TITLE = {Towards Nonmonotonic Relational Learning from Knowledge Graphs}, AUTHOR = {Tran, Hai Dang and Stepanova, Daria and Gad-Elrab, Mohamed and Lisi, Francesca A. and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {Springer}, YEAR = {2016}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {26th International Conference on Inductive Logic Programming (ILP 2016)}, SERIES = {Lecture Notes in Artificial Intelligence}, ADDRESS = {London, UK}, }
Endnote
%0 Conference Proceedings %A Tran, Hai Dang %A Stepanova, Daria %A Gad-Elrab, Mohamed %A Lisi, Francesca A. %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Towards Nonmonotonic Relational Learning from Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2DB1-E %D 2016 %B 26th International Conference on Inductive Logic Programming %Z date of event: 2016-09-04 - 2016-09-06 %C London, UK %B 26th International Conference on Inductive Logic Programming %I Springer %B Lecture Notes in Artificial Intelligence
[87]
Y. S. Uddin, V. Setty, Y. Zhao, R. Vitenberg, and N. Venkatasubramanian, “RichNote: Adaptive Selection and Delivery of Rich Media Notifications to Mobile Users,” in ICDCS 2016, 36th International Conference on Distributed Computing Systems, Nara, Japan, 2016.
Export
BibTeX
@inproceedings{UddinICDCS2016, TITLE = {{RichNote}: {A}daptive Selection and Delivery of Rich Media Notifications to Mobile Users}, AUTHOR = {Uddin, Yusuf Sarwar and Setty, Vinay and Zhao, Ye and Vitenberg, Roman and Venkatasubramanian, Nalini}, LANGUAGE = {eng}, ISSN = {1063-6927}, DOI = {10.1109/ICDCS.2016.107}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {ICDCS 2016, 36th International Conference on Distributed Computing Systems}, PAGES = {159--168}, ADDRESS = {Nara, Japan}, }
Endnote
%0 Conference Proceedings %A Uddin, Yusuf Sarwar %A Setty, Vinay %A Zhao, Ye %A Vitenberg, Roman %A Venkatasubramanian, Nalini %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T RichNote: Adaptive Selection and Delivery of Rich Media Notifications to Mobile Users : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-9AFE-C %R 10.1109/ICDCS.2016.107 %D 2016 %B 36th International Conference on Distributed Computing Systems %Z date of event: 2016-06-27 - 2016-06-30 %C Nara, Japan %B ICDCS 2016 %P 159 - 168 %I IEEE %@ false
[88]
J. Urbani, S. Dutta, S. Gurajada, and G. Weikum, “KOGNAC: Efficient Encoding of Large Knowledge Graphs,” in Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2016), New York, NY, USA, 2016.
Export
BibTeX
@inproceedings{UrbaniIJCAI2016, TITLE = {{KOGNAC}: {E}fficient Encoding of Large Knowledge Graphs}, AUTHOR = {Urbani, Jacopo and Dutta, Sourav and Gurajada, Sairam and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-57735-771-1}, URL = {http://www.ijcai.org/Proceedings/16/Papers/548.pdf}, PUBLISHER = {AAAI}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2016)}, EDITOR = {Kambhampati, Subbarao}, PAGES = {3896--3902}, ADDRESS = {New York, NY, USA}, }
Endnote
%0 Conference Proceedings %A Urbani, Jacopo %A Dutta, Sourav %A Gurajada, Sairam %A Weikum, Gerhard %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T KOGNAC: Efficient Encoding of Large Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A641-2 %U http://www.ijcai.org/Proceedings/16/Papers/548.pdf %D 2016 %B 25th International Joint Conference on Artificial Intelligence %Z date of event: 2016-07-09 - 2016-07-15 %C New York, NY, USA %B Twenty-Fifth International Joint Conference on Artificial Intelligence %E Kambhampati, Subbarao %P 3896 - 3902 %I AAAI %@ 978-1-57735-771-1
[89]
J. Urbani, S. Dutta, S. Gurajada, and G. Weikum, “KOGNAC: Efficient Encoding of Large Knowledge Graphs,” 2016. [Online]. Available: http://arxiv.org/abs/1604.04795. (arXiv: 1604.04795)
Abstract
Many Web applications require efficient querying of large Knowledge Graphs (KGs). We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques. In KOGNAC, frequent terms are detected with a frequency approximation algorithm and encoded to maximise compression. Infrequent terms are semantically grouped into ontological classes and encoded to increase data locality. We evaluated KOGNAC in combination with state-of-the-art RDF engines, and observed that it significantly improves SPARQL querying on KGs with up to 1B edges.
Export
BibTeX
@online{Urbani2016, TITLE = {{KOGNAC}: Efficient Encoding of Large Knowledge Graphs}, AUTHOR = {Urbani, Jacopo and Dutta, Sourav and Gurajada, Sairam and Weikum, Gerhard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1604.04795}, EPRINT = {1604.04795}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Many Web applications require efficient querying of large Knowledge Graphs (KGs). We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques. In KOGNAC, frequent terms are detected with a frequency approximation algorithm and encoded to maximise compression. Infrequent terms are semantically grouped into ontological classes and encoded to increase data locality. We evaluated KOGNAC in combination with state-of-the-art RDF engines, and observed that it significantly improves SPARQL querying on KGs with up to 1B edges.}, }
Endnote
%0 Report %A Urbani, Jacopo %A Dutta, Sourav %A Gurajada, Sairam %A Weikum, Gerhard %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T KOGNAC: Efficient Encoding of Large Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-01C1-3 %U http://arxiv.org/abs/1604.04795 %D 2016 %X Many Web applications require efficient querying of large Knowledge Graphs (KGs). We propose KOGNAC, a dictionary-encoding algorithm designed to improve SPARQL querying with a judicious combination of statistical and semantic techniques. In KOGNAC, frequent terms are detected with a frequency approximation algorithm and encoded to maximise compression. Infrequent terms are semantically grouped into ontological classes and encoded to increase data locality. We evaluated KOGNAC in combination with state-of-the-art RDF engines, and observed that it significantly improves SPARQL querying on KGs with up to 1B edges. %K Computer Science, Artificial Intelligence, cs.AI
[90]
Y. Wang, Z. Ren, M. Theobald, M. Dylla, and G. de Melo, “Summary Generation for Temporal Extractions,” in Database and Expert Systems Applications (DEXA 2016), Porto, Portugal, 2016.
Export
BibTeX
@inproceedings{Wang_DEXA2016, TITLE = {Summary Generation for Temporal Extractions}, AUTHOR = {Wang, Yafang and Ren, Zhaochun and Theobald, Martin and Dylla, Maximilian and de Melo, Gerard}, LANGUAGE = {eng}, ISBN = {978-3-319-44402-4}, DOI = {10.1007/978-3-319-44403-1_23}, PUBLISHER = {Springer}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {Database and Expert Systems Applications (DEXA 2016)}, EDITOR = {Hartmann, Sven and Ma, Hui}, PAGES = {370--386}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {9827}, ADDRESS = {Porto, Portugal}, }
Endnote
%0 Conference Proceedings %A Wang, Yafang %A Ren, Zhaochun %A Theobald, Martin %A Dylla, Maximilian %A de Melo, Gerard %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Summary Generation for Temporal Extractions : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2DE2-F %R 10.1007/978-3-319-44403-1_23 %D 2016 %B 27th International Conference on Database and Expert Systems Application %Z date of event: 2016-09-05 - 2016-09-08 %C Porto, Portugal %B Database and Expert Systems Applications %E Hartmann, Sven; Ma, Hui %P 370 - 386 %I Springer %@ 978-3-319-44402-4 %B Lecture Notes in Computer Science %N 9827
[91]
G. Weikum, J. Hoffart, and F. Suchanek, “Ten Years of Knowledge Harvesting: Lessons and Challenges,” Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, vol. 39, no. 3, 2016.
Export
BibTeX
@article{Weikum_Hoffart_Suchanek2016, TITLE = {Ten Years of Knowledge Harvesting: {L}essons and Challenges}, AUTHOR = {Weikum, Gerhard and Hoffart, Johannes and Suchanek, Fabian}, LANGUAGE = {eng}, URL = {http://sites.computer.org/debull/A16sept/p41.pdf}, PUBLISHER = {IEEE Computer Society}, ADDRESS = {Los Alamitos, CA}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Bulletin of the IEEE Computer Society Technical Committee on Data Engineering}, VOLUME = {39}, NUMBER = {3}, PAGES = {41--50}, }
Endnote
%0 Journal Article %A Weikum, Gerhard %A Hoffart, Johannes %A Suchanek, Fabian %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Télécom ParisTech %T Ten Years of Knowledge Harvesting: Lessons and Challenges : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A618-F %U http://sites.computer.org/debull/A16sept/p41.pdf %7 2016 %D 2016 %J Bulletin of the IEEE Computer Society Technical Committee on Data Engineering %V 39 %N 3 %& 41 %P 41 - 50 %I IEEE Computer Society %C Los Alamitos, CA
[92]
G. Weikum, “Die Abteilung Datenbanken und Informationssysteme am Max-Planck-Institut für Informatik,” Datenbank Spektrum, vol. 16, no. 1, 2016.
Export
BibTeX
@article{WeikumDBSpektrum2016, TITLE = {{Die Abteilung Datenbanken und Informationssysteme am Max-Planck-Institut f{\"u}r Informatik}}, AUTHOR = {Weikum, Gerhard}, LANGUAGE = {deu}, DOI = {10.1007/s13222-016-0211-z}, PUBLISHER = {Springer}, ADDRESS = {Berlin}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Datenbank Spektrum}, VOLUME = {16}, NUMBER = {1}, PAGES = {77--82}, }
Endnote
%0 Journal Article %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society %T Die Abteilung Datenbanken und Informationssysteme am Max-Planck-Institut für Informatik : %G deu %U http://hdl.handle.net/11858/00-001M-0000-002B-0194-B %R 10.1007/s13222-016-0211-z %7 2016 %D 2016 %J Datenbank Spektrum %V 16 %N 1 %& 77 %P 77 - 82 %I Springer %C Berlin
[93]
B. A. Wójciak, “Spaghetti: Finding Storylines in Large Collections of Documents,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{WojciakMSc2016, TITLE = {Spaghetti: Finding Storylines in Large Collections of Documents}, AUTHOR = {W{\'o}jciak, Beata Anna}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Wójciak, Beata Anna %Y Vreeken, Jilles %A referee: Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Spaghetti: Finding Storylines in Large Collections of Documents : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5F3F-3 %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master
[94]
H. Wu, M. Sun, J. Vreeken, N. Tatti, C. North, and N. Ramakrishnan, “Interactive and Iterative Discovery of Entity Network Subgraphs,” 2016. [Online]. Available: http://arxiv.org/abs/1608.03889. (arXiv: 1608.03889)
Abstract
Graph mining to extract interesting components has been studied in various guises, e.g., communities, dense subgraphs, cliques. However, most existing works are based on notions of frequency and connectivity and do not capture subjective interestingness from a user's viewpoint. Furthermore, existing approaches to mine graphs are not interactive and cannot incorporate user feedbacks in any natural manner. In this paper, we address these gaps by proposing a graph maximum entropy model to discover surprising connected subgraph patterns from entity graphs. This model is embedded in an interactive visualization framework to enable human-in-the-loop, model-guided data exploration. Using case studies on real datasets, we demonstrate how interactions between users and the maximum entropy model lead to faster and explainable conclusions.
Export
BibTeX
@online{Wu1608.03889, TITLE = {Interactive and Iterative Discovery of Entity Network Subgraphs}, AUTHOR = {Wu, Hao and Sun, Maoyuan and Vreeken, Jilles and Tatti, Nikolaj and North, Chris and Ramakrishnan, Naren}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1608.03889}, EPRINT = {1608.03889}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Graph mining to extract interesting components has been studied in various guises, e.g., communities, dense subgraphs, cliques. However, most existing works are based on notions of frequency and connectivity and do not capture subjective interestingness from a user's viewpoint. Furthermore, existing approaches to mine graphs are not interactive and cannot incorporate user feedbacks in any natural manner. In this paper, we address these gaps by proposing a graph maximum entropy model to discover surprising connected subgraph patterns from entity graphs. This model is embedded in an interactive visualization framework to enable human-in-the-loop, model-guided data exploration. Using case studies on real datasets, we demonstrate how interactions between users and the maximum entropy model lead to faster and explainable conclusions.}, }
Endnote
%0 Report %A Wu, Hao %A Sun, Maoyuan %A Vreeken, Jilles %A Tatti, Nikolaj %A North, Chris %A Ramakrishnan, Naren %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Interactive and Iterative Discovery of Entity Network Subgraphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A939-F %U http://arxiv.org/abs/1608.03889 %D 2016 %X Graph mining to extract interesting components has been studied in various guises, e.g., communities, dense subgraphs, cliques. However, most existing works are based on notions of frequency and connectivity and do not capture subjective interestingness from a user's viewpoint. Furthermore, existing approaches to mine graphs are not interactive and cannot incorporate user feedbacks in any natural manner. In this paper, we address these gaps by proposing a graph maximum entropy model to discover surprising connected subgraph patterns from entity graphs. This model is embedded in an interactive visualization framework to enable human-in-the-loop, model-guided data exploration. Using case studies on real datasets, we demonstrate how interactions between users and the maximum entropy model lead to faster and explainable conclusions. %K cs.SI,Computer Science, Databases, cs.DB
[95]
H. Wu, Y. Ning, P. Chakraborty, J. Vreeken, N. Tatti, and N. Ramakrishnan, “Generating Realistic Synthetic Population Datasets,” 2016. [Online]. Available: http://arxiv.org/abs/1602.06844. (arXiv: 1602.06844)
Abstract
Modern studies of societal phenomena rely on the availability of large datasets capturing attributes and activities of synthetic, city-level, populations. For instance, in epidemiology, synthetic population datasets are necessary to study disease propagation and intervention measures before implementation. In social science, synthetic population datasets are needed to understand how policy decisions might affect preferences and behaviors of individuals. In public health, synthetic population datasets are necessary to capture diagnostic and procedural characteristics of patient records without violating confidentialities of individuals. To generate such datasets over a large set of categorical variables, we propose the use of the maximum entropy principle to formalize a generative model such that in a statistically well-founded way we can optimally utilize given prior information about the data, and are unbiased otherwise. An efficient inference algorithm is designed to estimate the maximum entropy model, and we demonstrate how our approach is adept at estimating underlying data distributions. We evaluate this approach against both simulated data and on US census datasets, and demonstrate its feasibility using an epidemic simulation application.
Export
BibTeX
@online{Wu_arXiv2016, TITLE = {Generating Realistic Synthetic Population Datasets}, AUTHOR = {Wu, Hao and Ning, Yue and Chakraborty, Prithwish and Vreeken, Jilles and Tatti, Nikolaj and Ramakrishnan, Naren}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/1602.06844}, EPRINT = {1602.06844}, EPRINTTYPE = {arXiv}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Modern studies of societal phenomena rely on the availability of large datasets capturing attributes and activities of synthetic, city-level, populations. For instance, in epidemiology, synthetic population datasets are necessary to study disease propagation and intervention measures before implementation. In social science, synthetic population datasets are needed to understand how policy decisions might affect preferences and behaviors of individuals. In public health, synthetic population datasets are necessary to capture diagnostic and procedural characteristics of patient records without violating confidentialities of individuals. To generate such datasets over a large set of categorical variables, we propose the use of the maximum entropy principle to formalize a generative model such that in a statistically well-founded way we can optimally utilize given prior information about the data, and are unbiased otherwise. An efficient inference algorithm is designed to estimate the maximum entropy model, and we demonstrate how our approach is adept at estimating underlying data distributions. We evaluate this approach against both simulated data and on US census datasets, and demonstrate its feasibility using an epidemic simulation application.}, }
Endnote
%0 Report %A Wu, Hao %A Ning, Yue %A Chakraborty, Prithwish %A Vreeken, Jilles %A Tatti, Nikolaj %A Ramakrishnan, Naren %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Generating Realistic Synthetic Population Datasets : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-08F9-B %U http://arxiv.org/abs/1602.06844 %D 2016 %X Modern studies of societal phenomena rely on the availability of large datasets capturing attributes and activities of synthetic, city-level, populations. For instance, in epidemiology, synthetic population datasets are necessary to study disease propagation and intervention measures before implementation. In social science, synthetic population datasets are needed to understand how policy decisions might affect preferences and behaviors of individuals. In public health, synthetic population datasets are necessary to capture diagnostic and procedural characteristics of patient records without violating confidentialities of individuals. To generate such datasets over a large set of categorical variables, we propose the use of the maximum entropy principle to formalize a generative model such that in a statistically well-founded way we can optimally utilize given prior information about the data, and are unbiased otherwise. An efficient inference algorithm is designed to estimate the maximum entropy model, and we demonstrate how our approach is adept at estimating underlying data distributions. We evaluate this approach against both simulated data and on US census datasets, and demonstrate its feasibility using an epidemic simulation application. %K Computer Science, Databases, cs.DB
[96]
M. Yahya, “Question Answering and Query Processing for Extended Knowledge Graphs,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@phdthesis{yahyaphd2016, TITLE = {Question Answering and Query Processing for Extended Knowledge Graphs}, AUTHOR = {Yahya, Mohamed}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Yahya, Mohamed %Y Weikum, Gerhard %A referee: Schütze, Hinrich %+ Databases and Information Systems, MPI for Informatics, Max Planck Society International Max Planck Research School, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Question Answering and Query Processing for Extended Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-48C2-7 %I Universität des Saarlandes %C Saarbrücken %D 2016 %P x, 160 p. %V phd %9 phd %U http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=dehttp://scidok.sulb.uni-saarland.de/volltexte/2016/6476/
[97]
M. Yahya, K. Berberich, M. Ramanath, and G. Weikum, “Exploratory Querying of Extended Knowledge Graphs,” Proceedings of the VLDB Endowment (Proc. VLDB 2016), vol. 9, no. 1, 2016.
Export
BibTeX
@article{YahyaVLDB2016, TITLE = {Exploratory Querying of Extended Knowledge Graphs}, AUTHOR = {Yahya, Mohamed and Berberich, Klaus and Ramanath, Maya and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, JOURNAL = {Proceedings of the VLDB Endowment (Proc. VLDB)}, VOLUME = {9}, NUMBER = {1}, PAGES = {1521--1524}, BOOKTITLE = {Proceedings of the 42nd International Conference on Very Large Data Bases (VLDB 2016)}, EDITOR = {Chaudhuri, Surajit and Haritsa, Jayant}, }
Endnote
%0 Journal Article %A Yahya, Mohamed %A Berberich, Klaus %A Ramanath, Maya %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Exploratory Querying of Extended Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-A61C-7 %7 2016 %D 2016 %J Proceedings of the VLDB Endowment %O PVLDB %V 9 %N 1 %& 1521 %P 1521 - 1524 %I ACM %C New York, NY %B Proceedings of the 42nd International Conference on Very Large Data Bases %O VLDB 2016 New Delhi, India, September 5 - 9, 2016 %U http://www.vldb.org/pvldb/vol9/p1521-yahya.pdf
[98]
M. Yahya, D. Barbosa, K. Berberich, Q. Wang, and G. Weikum, “Relationship Queries on Extended Knowledge Graphs,” in WSDM’16, 9th ACM International Conference on Web Search and Data Mining, San Francisco, CA, USA, 2016.
Export
BibTeX
@inproceedings{YahyaWSDM2016, TITLE = {Relationship Queries on Extended Knowledge Graphs}, AUTHOR = {Yahya, Mohamed and Barbosa, Denilson and Berberich, Klaus and Wang, Quiyue and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-1-4503-3716-8}, DOI = {10.1145/2835776.2835795}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WSDM'16, 9th ACM International Conference on Web Search and Data Mining}, PAGES = {605--614}, ADDRESS = {San Francisco, CA, USA}, }
Endnote
%0 Conference Proceedings %A Yahya, Mohamed %A Barbosa, Denilson %A Berberich, Klaus %A Wang, Quiyue %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Relationship Queries on Extended Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0029-ABAA-0 %R 10.1145/2835776.2835795 %D 2016 %B 9th ACM International Conference on Web Search and Data Mining %Z date of event: 2016-02-22 - 2016-02-25 %C San Francisco, CA, USA %B WSDM'16 %P 605 - 614 %I ACM %@ 978-1-4503-3716-8
[99]
L. Zervakis, C. Tryfonopoulos, V. Setty, S. Seufert, and S. Skiadopoulos, “Towards Publish/Subscribe Functionality on Graphs,” in Proceedings of the Workshops of the EDBT/ICDT 2016 Joint Conference, Bordeaux, France, 2016.
Export
BibTeX
@inproceedings{DBLP:conf/edbt/ZervakisTSSS16, TITLE = {Towards Publish/Subscribe Functionality on Graphs}, AUTHOR = {Zervakis, Lefteris and Tryfonopoulos, Christos and Setty, Vinay and Seufert, Stephan and Skiadopoulos, Spiros}, LANGUAGE = {eng}, ISSN = {1613-0073}, URL = {urn:nbn:de:0074-1558-2}, PUBLISHER = {CEUR-WS.org}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Workshops of the EDBT/ICDT 2016 Joint Conference}, EDITOR = {Palpanas, Thermis and Stefanidis, Kostas}, EID = {13}, SERIES = {CEUR Workshop Proceedings}, VOLUME = {1558}, ADDRESS = {Bordeaux, France}, }
Endnote
%0 Conference Proceedings %A Zervakis, Lefteris %A Tryfonopoulos, Christos %A Setty, Vinay %A Seufert, Stephan %A Skiadopoulos, Spiros %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Towards Publish/Subscribe Functionality on Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1CAE-1 %D 2016 %B 2nd International Workshop on Preservation of Evolving Big Data %Z date of event: 2016-03-15 - 2016-03-15 %C Bordeaux, France %B Proceedings of the Workshops of the EDBT/ICDT 2016 Joint Conference %E Palpanas, Thermis; Stefanidis, Kostas %Z sequence number: 13 %I CEUR-WS.org %B CEUR Workshop Proceedings %N 1558 %@ false
[100]
H. Zhang and V. Setty, “Finding Diverse Needles in a Haystack of Comments -- Social Media Exploration for News,” in WebSci’16, ACM Web Science Conference, Hannover, Germany, 2016.
Export
BibTeX
@inproceedings{ZhangWebSci2016, TITLE = {Finding Diverse Needles in a Haystack of Comments -- Social Media Exploration for News}, AUTHOR = {Zhang, Hang and Setty, Vinay}, LANGUAGE = {eng}, ISBN = {978-1-4503-4208-7}, DOI = {10.1145/2908131.2908168}, PUBLISHER = {ACM}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, BOOKTITLE = {WebSci'16, ACM Web Science Conference}, PAGES = {286--290}, ADDRESS = {Hannover, Germany}, }
Endnote
%0 Conference Proceedings %A Zhang, Hang %A Setty, Vinay %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Finding Diverse Needles in a Haystack of Comments -- Social Media Exploration for News : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002B-020A-C %R 10.1145/2908131.2908168 %D 2016 %B ACM Web Science Conference %Z date of event: 2016-05-22 - 2016-05-25 %C Hannover, Germany %B WebSci'16 %P 286 - 290 %I ACM %@ 978-1-4503-4208-7
[101]
H. Zhang, “Diversified Social Media Retrieval for News Stories,” Universität des Saarlandes, Saarbrücken, 2016.
Export
BibTeX
@mastersthesis{ZhangMSc2016, TITLE = {Diversified Social Media Retrieval for News Stories}, AUTHOR = {Zhang, Hang}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, DATE = {2016}, }
Endnote
%0 Thesis %A Zhang, Hang %Y Neumann, Günther %A referee: Weikum, Gerhard %A referee: Setty, Vinay %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Diversified Social Media Retrieval for News Stories : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-48D3-E %I Universität des Saarlandes %C Saarbrücken %D 2016 %V master %9 master