2017
[1]
A. Abujabal, M. Yahya, M. Riedewald, and G. Weikum, “Automated Template Generation for Question Answering over Knowledge Graphs,” in WWW’17, 26th International Conference on World Wide Web, Perth, Australia. (Accepted/in press)
Export
BibTeX
@inproceedings{AbujabalWWW2017, TITLE = {Automated Template Generation for Question Answering over Knowledge Graphs}, AUTHOR = {Abujabal, Abdalghani and Yahya, Mohamed and Riedewald, Mirek and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {ACM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WWW'17, 26th International Conference on World Wide Web}, ADDRESS = {Perth, Australia}, }
Endnote
%0 Conference Proceedings %A Abujabal, Abdalghani %A Yahya, Mohamed %A Riedewald, Mirek %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 Automated Template Generation for Question Answering over Knowledge Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4F9C-E %D 2017 %B 26th International Conference on World Wide Web %Z date of event: 2017-04-03 - 2017-04-07 %C Perth, Australia %B WWW'17 %I ACM
[2]
P. Agarwal and J. Strötgen, “Tiwiki: Searching Wikipedia with Temporal Constraints,” in 7th Temporal Web Analytics Workshop (TempWeb 2017), Perth, Australia. (Accepted/in press)
Export
BibTeX
@inproceedings{AgarwalStroetgen2017_TempWeb, TITLE = {Tiwiki: Searching {W}ikipedia with Temporal Constraints}, AUTHOR = {Agarwal, Prabal and Str{\"o}tgen, Jannik}, LANGUAGE = {eng}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {7th Temporal Web Analytics Workshop (TempWeb 2017)}, ADDRESS = {Perth, Australia}, }
Endnote
%0 Conference Proceedings %A Agarwal, Prabal %A Strötgen, Jannik %+ 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 %T Tiwiki: Searching Wikipedia with Temporal Constraints : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-53AE-9 %D 2017 %8 31.01.2017 %B 7th Temporal Web Analytics Workshop %Z date of event: 2017-04-03 - 2017-04-07 %C Perth, Australia %B 7th Temporal Web Analytics Workshop
[3]
R. Andrade and J. Strötgen, “All Dates Lead to Rome: Extracting and Explaining Temporal References in Street Names,” in WWW’17 Companion, Perth, Australia. (Accepted/in press)
Export
BibTeX
@inproceedings{AndradeWWW2017, TITLE = {All Dates Lead to {R}ome: {E}xtracting and Explaining Temporal References in Street Names}, AUTHOR = {Andrade, Rosita and Str{\"o}tgen, Jannik}, LANGUAGE = {eng}, PUBLISHER = {ACM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WWW'17 Companion}, ADDRESS = {Perth, Australia}, }
Endnote
%0 Conference Proceedings %A Andrade, Rosita %A Strötgen, Jannik %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T All Dates Lead to Rome: Extracting and Explaining Temporal References in Street Names : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-62AE-1 %D 2017 %B 26th International Conference on World Wide Web %Z date of event: 2017-04-03 - 2017-04-07 %C Perth, Australia %B WWW'17 Companion %I ACM
[4]
R. Bertens, J. Vreeken, and A. Siebes, “Efficiently Discovering Unexpected Pattern Co-Occurrences,” in Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), Houston, TX, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{bertens:17:upc, TITLE = {Efficiently Discovering Unexpected Pattern Co-Occurrences}, AUTHOR = {Bertens, Roel and Vreeken, Jilles and Siebes, Arno}, LANGUAGE = {eng}, PUBLISHER = {SIAM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017)}, ADDRESS = {Houston, TX, 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 Efficiently Discovering Unexpected Pattern Co-Occurrences : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4BDF-7 %D 2017 %B 17th SIAM International Conference on Data Mining %Z date of event: 2017-04-27 - 2017-04-29 %C Houston, TX, USA %B Proceedings of the Seventeenth SIAM International Conference on Data Mining %I SIAM
[5]
A. Bhattacharyya and J. Vreeken, “Efficiently Summarising Event Sequences with Rich Interleaving Patterns,” in Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), Houston, TX, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{bhattacharyya:17:squish, TITLE = {Efficiently Summarising Event Sequences with Rich Interleaving Patterns}, AUTHOR = {Bhattacharyya, Apratim and Vreeken, Jilles}, LANGUAGE = {eng}, PUBLISHER = {SIAM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017)}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Bhattacharyya, Apratim %A Vreeken, Jilles %+ Databases and Information Systems, 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 Efficiently Summarising Event Sequences with Rich Interleaving Patterns : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4BDC-D %D 2017 %B 17th SIAM International Conference on Data Mining %Z date of event: 2017-04-27 - 2017-04-29 %C Houston, TX, USA %B Proceedings of the Seventeenth SIAM International Conference on Data Mining %I SIAM
[6]
K. Budhathoki and J. Vreeken, “Causal Inference by Compression,” in 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona, Spain, 2017.
Export
BibTeX
@inproceedings{budhathoki:16:origo, TITLE = {Causal Inference by Compression}, AUTHOR = {Budhathoki, Kailash and Vreeken, Jilles}, LANGUAGE = {eng}, ISBN = {978-1-5090-5473-2}, DOI = {10.1109/ICDM.2016.0015}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {16th IEEE International Conference on Data Mining (ICDM 2016)}, EDITOR = {Bonchi, Francesco and Domingo-Ferrer, Josep and Baeza-Yates, Ricardo and Zhou, Zhi-Hua and Wu, Xindong}, PAGES = {41--50}, ADDRESS = {Barcelona, Spain}, }
Endnote
%0 Conference Proceedings %A Budhathoki, Kailash %A Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Causal Inference by Compression : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1CC0-6 %R 10.1109/ICDM.2016.0015 %D 2017 %8 02.02.2017 %B 16th International Conference on Data Mining %Z date of event: 2016-12-12 - 2016-12-15 %C Barcelona, Spain %B 16th IEEE International Conference on Data Mining %E Bonchi, Francesco; Domingo-Ferrer, Josep; Baeza-Yates, Ricardo; Zhou, Zhi-Hua; Wu, Xindong %P 41 - 50 %I IEEE %@ 978-1-5090-5473-2
[7]
K. Budhathoki and J. Vreeken, “Correlation by Compression,” in Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), Houston, TX, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{budhathoki:17:cbc, TITLE = {Correlation by Compression}, AUTHOR = {Budhathoki, Kailash and Vreeken, Jilles}, LANGUAGE = {eng}, PUBLISHER = {SIAM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017)}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Budhathoki, Kailash %A Vreeken, Jilles %+ Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Correlation by Compression : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4BD8-6 %D 2017 %B 17th SIAM International Conference on Data Mining %Z date of event: 2017-04-27 - 2017-04-29 %C Houston, TX, USA %B Proceedings of the Seventeenth SIAM International Conference on Data Mining %I SIAM
[8]
C. X. Chu, N. Tandon, and G. Weikum, “Distilling Task Knowledge from How-To Communities,” in WWW’17, 26th International Conference on World Wide Web, Perth, Australia. (Accepted/in press)
Export
BibTeX
@inproceedings{Cuong:WWW2017, TITLE = {Distilling Task Knowledge from How-To Communities}, AUTHOR = {Chu, Cuong Xuan and Tandon, Niket and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {ACM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WWW'17, 26th International Conference on World Wide Web}, ADDRESS = {Perth, Australia}, }
Endnote
%0 Conference Proceedings %A Chu, Cuong Xuan %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 Distilling Task Knowledge from How-To Communities : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-54BE-E %D 2017 %B 26th International Conference on World Wide Web %Z date of event: 2017-04-03 - 2017-04-07 %C Perth, Australia %B WWW'17 %I ACM
[9]
C. Costa, G. Chatzimilioudis, D. Zeinalipour-Yazti, and M. F. Mokbel, “Efficient Exploration of Telco Big Data with Compression and Decaying,” in 33rd IEEE International Conference on Data Engineering (ICDE 2017), San Diego, CA, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{icde17-spate, TITLE = {Efficient Exploration of Telco Big Data with Compression and Decaying}, AUTHOR = {Costa, Constantinos and Chatzimilioudis, Georgios and Zeinalipour-Yazti, Demetrios and Mokbel, Mohamed F.}, LANGUAGE = {eng}, PUBLISHER = {IEEE}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {33rd IEEE International Conference on Data Engineering (ICDE 2017)}, ADDRESS = {San Diego, CA, USA}, }
Endnote
%0 Conference Proceedings %A Costa, Constantinos %A Chatzimilioudis, Georgios %A Zeinalipour-Yazti, Demetrios %A Mokbel, Mohamed F. %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Efficient Exploration of Telco Big Data with Compression and Decaying : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-62B3-4 %D 2017 %B 33rd IEEE International Conference on Data Engineering %Z date of event: 2017-04-19 - 2017-04-22 %C San Diego, CA, USA %B 33rd IEEE International Conference on Data Engineering %I IEEE
[10]
C. Costa, G. Chatzimilioudis, D. Zeinalipour-Yazti, and M. F. Mokbel, “SPATE: Compacting and Exploring Telco Big Data,” in 33rd IEEE International Conference on Data Engineering (ICDE 2017), San Diego, CA, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{icde17-spate-demo, TITLE = {{SPATE}: Compacting and Exploring Telco Big Data}, AUTHOR = {Costa, Constantinos and Chatzimilioudis, Georgios and Zeinalipour-Yazti, Demetrios and Mokbel, Mohamed F.}, LANGUAGE = {eng}, PUBLISHER = {IEEE}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {33rd IEEE International Conference on Data Engineering (ICDE 2017)}, ADDRESS = {San Diego, CA, USA}, }
Endnote
%0 Conference Proceedings %A Costa, Constantinos %A Chatzimilioudis, Georgios %A Zeinalipour-Yazti, Demetrios %A Mokbel, Mohamed F. %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T SPATE: Compacting and Exploring Telco Big Data : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-62BA-5 %D 2017 %B 33rd IEEE International Conference on Data Engineering %Z date of event: 2017-04-19 - 2017-04-22 %C San Diego, CA, USA %B 33rd IEEE International Conference on Data Engineering %I IEEE
[11]
S. Dutta, “Efficient knowledge Management for Named Entities from Text,” Universität des Saarlandes, Saarbrücken, 2017.
Abstract
The evolution of search from keywords to entities has necessitated the efficient harvesting and management of entity-centric information for constructing knowledge bases catering to various applications such as semantic search, question answering, and information retrieval. The vast amounts of natural language texts available across diverse domains on the Web provide rich sources for discovering facts about named entities such as people, places, and organizations. A key challenge, in this regard, entails the need for precise identification and disambiguation of entities across documents for extraction of attributes/relations and their proper representation in knowledge bases. Additionally, the applicability of such repositories not only involves the quality and accuracy of the stored information, but also storage management and query processing efficiency. This dissertation aims to tackle the above problems by presenting efficient approaches for entity-centric knowledge acquisition from texts and its representation in knowledge repositories. This dissertation presents a robust approach for identifying text phrases pertaining to the same named entity across huge corpora, and their disambiguation to canonical entities present in a knowledge base, by using enriched semantic contexts and link validation encapsulated in a hierarchical clustering framework. This work further presents language and consistency features for classification models to compute the credibility of obtained textual facts, ensuring quality of the extracted information. Finally, an encoding algorithm, using frequent term detection and improved data locality, to represent entities for enhanced knowledge base storage and query performance is presented.
Export
BibTeX
@phdthesis{duttaphd17, TITLE = {Efficient knowledge Management for Named Entities from Text}, AUTHOR = {Dutta, Sourav}, LANGUAGE = {eng}, URL = {urn:nbn:de:bsz:291-scidok-67924}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, DATE = {2017}, ABSTRACT = {The evolution of search from keywords to entities has necessitated the efficient harvesting and management of entity-centric information for constructing knowledge bases catering to various applications such as semantic search, question answering, and information retrieval. The vast amounts of natural language texts available across diverse domains on the Web provide rich sources for discovering facts about named entities such as people, places, and organizations. A key challenge, in this regard, entails the need for precise identification and disambiguation of entities across documents for extraction of attributes/relations and their proper representation in knowledge bases. Additionally, the applicability of such repositories not only involves the quality and accuracy of the stored information, but also storage management and query processing efficiency. This dissertation aims to tackle the above problems by presenting efficient approaches for entity-centric knowledge acquisition from texts and its representation in knowledge repositories. This dissertation presents a robust approach for identifying text phrases pertaining to the same named entity across huge corpora, and their disambiguation to canonical entities present in a knowledge base, by using enriched semantic contexts and link validation encapsulated in a hierarchical clustering framework. This work further presents language and consistency features for classification models to compute the credibility of obtained textual facts, ensuring quality of the extracted information. Finally, an encoding algorithm, using frequent term detection and improved data locality, to represent entities for enhanced knowledge base storage and query performance is presented.}, }
Endnote
%0 Thesis %A Dutta, Sourav %Y Weikum, Gerhard %A referee: Nejdl, Wolfgang %A referee: Berberich, Klaus %+ 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 Databases and Information Systems, MPI for Informatics, Max Planck Society %T Efficient knowledge Management for Named Entities from Text : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-A793-E %U urn:nbn:de:bsz:291-scidok-67924 %I Universität des Saarlandes %C Saarbrücken %D 2017 %P xv, 134 p. %V phd %9 phd %X The evolution of search from keywords to entities has necessitated the efficient harvesting and management of entity-centric information for constructing knowledge bases catering to various applications such as semantic search, question answering, and information retrieval. The vast amounts of natural language texts available across diverse domains on the Web provide rich sources for discovering facts about named entities such as people, places, and organizations. A key challenge, in this regard, entails the need for precise identification and disambiguation of entities across documents for extraction of attributes/relations and their proper representation in knowledge bases. Additionally, the applicability of such repositories not only involves the quality and accuracy of the stored information, but also storage management and query processing efficiency. This dissertation aims to tackle the above problems by presenting efficient approaches for entity-centric knowledge acquisition from texts and its representation in knowledge repositories. This dissertation presents a robust approach for identifying text phrases pertaining to the same named entity across huge corpora, and their disambiguation to canonical entities present in a knowledge base, by using enriched semantic contexts and link validation encapsulated in a hierarchical clustering framework. This work further presents language and consistency features for classification models to compute the credibility of obtained textual facts, ensuring quality of the extracted information. Finally, an encoding algorithm, using frequent term detection and improved data locality, to represent entities for enhanced knowledge base storage and query performance is presented. %U http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=dehttp://scidok.sulb.uni-saarland.de/volltexte/2017/6792/
[12]
E. Galbrun and P. Miettinen, “Analysing Political Opinions Using Redescription Mining,” in 16th IEEE International Conference on Data Mining Workshops (ICDMW 2016), Barcelona, Spain, 2017.
Export
BibTeX
@inproceedings{galbrun16analysing, TITLE = {Analysing Political Opinions Using Redescription Mining}, AUTHOR = {Galbrun, Esther and Miettinen, Pauli}, LANGUAGE = {eng}, ISBN = {978-1-5090-5910-2}, DOI = {10.1109/ICDMW.2016.121}, PUBLISHER = {IEEE}, YEAR = {2015}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {16th IEEE International Conference on Data Mining Workshops (ICDMW 2016)}, EDITOR = {Domeniconi, Carlotta and Gullo, Francesco and Bonchi, Francesco and Domingo-Ferrer, Josep and Baeza-Yates, Ricardo and Zhou, Zhi-Hua and Wu, Xindong}, PAGES = {422--427}, ADDRESS = {Barcelona, Spain}, }
Endnote
%0 Conference Proceedings %A Galbrun, Esther %A Miettinen, Pauli %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Analysing Political Opinions Using Redescription Mining : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2247-5 %R 10.1109/ICDMW.2016.121 %D 2017 %8 02.02.2017 %B 16th International Conference on Data Mining %Z date of event: 2015-12-12 - 2015-12-15 %C Barcelona, Spain %B 16th IEEE International Conference on Data Mining Workshops %E Domeniconi, Carlotta; Gullo, Francesco; Bonchi, Francesco; Domingo-Ferrer, Josep; Baeza-Yates, Ricardo; Zhou, Zhi-Hua; Wu, Xindong %P 422 - 427 %I IEEE %@ 978-1-5090-5910-2
[13]
B. Goldsmith, M. Boley, J. Vreeken, M. Scheffler, and L. Ghiringhelli,, “Uncovering Structure-property Relationships of Materials by Subgroup Discovery,” New Journal of Physics, vol. 19, no. 1, 2017.
Export
BibTeX
@article{goldsmith:17:gold, TITLE = {Uncovering Structure-property Relationships of Materials by Subgroup Discovery}, AUTHOR = {Goldsmith, Brian and Boley, Mario and Vreeken, Jilles and Scheffler, Matthias and Ghiringhelli,, Luca}, LANGUAGE = {eng}, ISSN = {1367-2630}, DOI = {10.1088/1367-2630/aa57c2}, PUBLISHER = {IOP Publishing}, ADDRESS = {Bristol}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, JOURNAL = {New Journal of Physics}, VOLUME = {19}, NUMBER = {1}, EID = {013031}, }
Endnote
%0 Journal Article %A Goldsmith, Brian %A Boley, Mario %A Vreeken, Jilles %A Scheffler, Matthias %A Ghiringhelli,, Luca %+ External Organizations 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 Uncovering Structure-property Relationships of Materials by Subgroup Discovery : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4BF5-4 %R 10.1088/1367-2630/aa57c2 %7 2017 %D 2017 %J New Journal of Physics %O New J. Phys. %V 19 %N 1 %Z sequence number: 013031 %I IOP Publishing %C Bristol %@ false %U http://iopscience.iop.org/article/10.1088/1367-2630/aa57c2
[14]
S. Gurajada, “Distributed Querying of Large Labeled Graphs,” Universität des Saarlandes, Saarbrücken, 2017.
Abstract
Graph is a vital abstract data type that has profound significance in several applications. Because of its versitality, graphs have been adapted into several different forms and one such adaption with many practical applications is the “Labeled Graph”, where vertices and edges are labeled. An enormous research effort has been invested in to the task of managing and querying graphs, yet a lot challenges are left unsolved. In this thesis, we advance the state-of-the-art for the following query models, and propose a distributed solution to process them in an efficient and scalable manner. • Set Reachability. We formalize and investigate a generalization of the basic notion of reachability, called set reachability. Set reachability deals with finding all reachable pairs for a given source and target sets. We present a non-iterative distributed solution that takes only a single round of communication for any set reachability query. This is achieved by precomputation, replication, and indexing of partial reachabilities among the boundary vertices. • Basic Graph Patterns (BGP). Supported by majority of query languages, BGP queries are a common mode of querying knowledge graphs, biological datasets, etc. We present a novel distributed architecture that relies on the concepts of asynchronous executions, join-ahead pruning, and a multi-threaded query processing framework to process BGP queries in an efficient and scalable manner. • Generalized Graph Patterns (GGP). These queries combine the semantics of pattern matching and navigational queries, and are popular in scenarios where the schema of an underlying graph is either unknown or partially known. We present a distributed solution with bimodal indexing layout that individually support efficient processing of BGP queries and navigational queries. Furthermore, we design a unified query optimizer and a processor to efficiently process GGP queries and also in a scalable manner. To this end, we propose a prototype distributed engine, coined “TriAD” (Triple Asynchronous and Distributed) that supports all the aforementioned query models. We also provide a detailed empirical evaluation of TriAD in comparison to several state-of-the-art systems over multiple real-world and synthetic datasets.
Export
BibTeX
@phdthesis{guraphd2017, TITLE = {Distributed Querying of Large Labeled Graphs}, AUTHOR = {Gurajada, Sairam}, LANGUAGE = {eng}, URL = {urn:nbn:de:bsz:291-scidok-67738}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, DATE = {2017}, ABSTRACT = {Graph is a vital abstract data type that has profound significance in several applications. Because of its versitality, graphs have been adapted into several different forms and one such adaption with many practical applications is the {\textquotedblleft}Labeled Graph{\textquotedblright}, where vertices and edges are labeled. An enormous research effort has been invested in to the task of managing and querying graphs, yet a lot challenges are left unsolved. In this thesis, we advance the state-of-the-art for the following query models, and propose a distributed solution to process them in an efficient and scalable manner. \mbox{$\bullet$} Set Reachability. We formalize and investigate a generalization of the basic notion of reachability, called set reachability. Set reachability deals with finding all reachable pairs for a given source and target sets. We present a non-iterative distributed solution that takes only a single round of communication for any set reachability query. This is achieved by precomputation, replication, and indexing of partial reachabilities among the boundary vertices. \mbox{$\bullet$} Basic Graph Patterns (BGP). Supported by majority of query languages, BGP queries are a common mode of querying knowledge graphs, biological datasets, etc. We present a novel distributed architecture that relies on the concepts of asynchronous executions, join-ahead pruning, and a multi-threaded query processing framework to process BGP queries in an efficient and scalable manner. \mbox{$\bullet$} Generalized Graph Patterns (GGP). These queries combine the semantics of pattern matching and navigational queries, and are popular in scenarios where the schema of an underlying graph is either unknown or partially known. We present a distributed solution with bimodal indexing layout that individually support efficient processing of BGP queries and navigational queries. Furthermore, we design a unified query optimizer and a processor to efficiently process GGP queries and also in a scalable manner. To this end, we propose a prototype distributed engine, coined {\textquotedblleft}TriAD{\textquotedblright} (Triple Asynchronous and Distributed) that supports all the aforementioned query models. We also provide a detailed empirical evaluation of TriAD in comparison to several state-of-the-art systems over multiple real-world and synthetic datasets.}, }
Endnote
%0 Thesis %A Gurajada, Sairam %Y Theobald, Martin %A referee: Weikum, Gerhard %A referee: Özsu, M. Tamer %A referee: Michel, Sebastian %+ 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 External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T Distributed Querying of Large Labeled Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-8202-E %U urn:nbn:de:bsz:291-scidok-67738 %I Universität des Saarlandes %C Saarbrücken %D 2017 %P x, 167 p. %V phd %9 phd %X Graph is a vital abstract data type that has profound significance in several applications. Because of its versitality, graphs have been adapted into several different forms and one such adaption with many practical applications is the “Labeled Graph”, where vertices and edges are labeled. An enormous research effort has been invested in to the task of managing and querying graphs, yet a lot challenges are left unsolved. In this thesis, we advance the state-of-the-art for the following query models, and propose a distributed solution to process them in an efficient and scalable manner. • Set Reachability. We formalize and investigate a generalization of the basic notion of reachability, called set reachability. Set reachability deals with finding all reachable pairs for a given source and target sets. We present a non-iterative distributed solution that takes only a single round of communication for any set reachability query. This is achieved by precomputation, replication, and indexing of partial reachabilities among the boundary vertices. • Basic Graph Patterns (BGP). Supported by majority of query languages, BGP queries are a common mode of querying knowledge graphs, biological datasets, etc. We present a novel distributed architecture that relies on the concepts of asynchronous executions, join-ahead pruning, and a multi-threaded query processing framework to process BGP queries in an efficient and scalable manner. • Generalized Graph Patterns (GGP). These queries combine the semantics of pattern matching and navigational queries, and are popular in scenarios where the schema of an underlying graph is either unknown or partially known. We present a distributed solution with bimodal indexing layout that individually support efficient processing of BGP queries and navigational queries. Furthermore, we design a unified query optimizer and a processor to efficiently process GGP queries and also in a scalable manner. To this end, we propose a prototype distributed engine, coined “TriAD” (Triple Asynchronous and Distributed) that supports all the aforementioned query models. We also provide a detailed empirical evaluation of TriAD in comparison to several state-of-the-art systems over multiple real-world and synthetic datasets. %U http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=dehttp://scidok.sulb.uni-saarland.de/volltexte/2017/6773/
[15]
K. Hui and K. Berberich, “Low-Cost Preference Judgment via Ties,” in Advances in Information Retrieval (ECIR 2017), Aberdeen, Scotland, UK. (Accepted/in press)
Export
BibTeX
@inproceedings{hui2017short, TITLE = {Low-Cost Preference Judgment via Ties}, AUTHOR = {Hui, Kai and Berberich, Klaus}, LANGUAGE = {eng}, PUBLISHER = {Springer}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Information Retrieval (ECIR 2017)}, ADDRESS = {Aberdeen, Scotland, UK}, }
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 Low-Cost Preference Judgment via Ties : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-1F7B-A %D 2016 %8 02.12.2016 %B 39th European Conference on Information Retrieval %Z date of event: 2017-04-09 - 2017-04-13 %C Aberdeen, Scotland, UK %B Advances in Information Retrieval %I Springer
[16]
R. Jäschke, J. Strötgen, E. Krotova, and F. Fischer, “„Der Helmut Kohl unter den Brotaufstrichen“ - Zur Extraktion vossianischer Antonomasien aus großen Zeitungskorpora,” in DHd 2017, 4. Tagung des Verbands Digital Humanities im deutschsprachigen Raum e.V., Bern, Switzerland, 2017.
Export
BibTeX
@inproceedings{JaeschkeEtAl2017_DHD, TITLE = {{{``Der Helmut Kohl unter den Brotaufstrichen'' -- Zur Extraktion vossianischer Antonomasien aus gro{\ss}en Zeitungskorpora}}}, AUTHOR = {J{\"a}schke, Robert and Str{\"o}tgen, Jannik and Krotova, Elena and Fischer, Frank}, LANGUAGE = {deu}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {DHd 2017, 4. Tagung des Verbands Digital Humanities im deutschsprachigen Raum e.V.}, PAGES = {120--124}, ADDRESS = {Bern, Switzerland}, }
Endnote
%0 Conference Proceedings %A Jäschke, Robert %A Strötgen, Jannik %A Krotova, Elena %A Fischer, Frank %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T „Der Helmut Kohl unter den Brotaufstrichen“ - Zur Extraktion vossianischer Antonomasien aus großen Zeitungskorpora : %G deu %U http://hdl.handle.net/11858/00-001M-0000-002C-4E05-A %D 2017 %B 4. Tagung des Verbands Digital Humanities im deutschsprachigen Raum e.V. %Z date of event: 2017-02-13 - 2017-02-18 %C Bern, Switzerland %B DHd 2017 %P 120 - 124
[17]
J. Kalofolias, E. Galbrun, and P. Miettinen, “From Sets of Good Redescriptions to Good Sets of Redescriptions,” in 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona, Spain, 2017.
Export
BibTeX
@inproceedings{kalofolias16from, TITLE = {From Sets of Good Redescriptions to Good Sets of Redescriptions}, AUTHOR = {Kalofolias, Janis and Galbrun, Esther and Miettinen, Pauli}, LANGUAGE = {eng}, ISBN = {978-1-5090-5473-2}, DOI = {10.1109/ICDM.2016.0032}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {16th IEEE International Conference on Data Mining (ICDM 2016)}, PAGES = {211--220}, ADDRESS = {Barcelona, Spain}, }
Endnote
%0 Conference Proceedings %A Kalofolias, Janis %A Galbrun, Esther %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 From Sets of Good Redescriptions to Good Sets of Redescriptions : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-224D-A %R 10.1109/ICDM.2016.0032 %D 2017 %8 02.02.2017 %B 16th International Conference on Data Mining %Z date of event: 2016-12-12 - 2016-12-15 %C Barcelona, Spain %B 16th IEEE International Conference on Data Mining %P 211 - 220 %I IEEE %@ 978-1-5090-5473-2
[18]
L. Lange, “Time in Newspaper: A Large-Scale Analysis of Temporal Expressions in News Corpora,” Universität des Saarlandes, Saarbrücken, 2017.
Export
BibTeX
@mastersthesis{LangeBcS2017, TITLE = {Time in Newspaper: {A} Large-Scale Analysis of Temporal Expressions in News Corpora}, AUTHOR = {Lange, Lukas}, LANGUAGE = {eng}, SCHOOL = {Universit{\"a}t des Saarlandes}, ADDRESS = {Saarbr{\"u}cken}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, DATE = {2017}, TYPE = {Bachelor's thesis}, }
Endnote
%0 Thesis %A Lange, Lukas %Y Strötgen, Jannik %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 Time in Newspaper: A Large-Scale Analysis of Temporal Expressions in News Corpora : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-5D08-B %I Universität des Saarlandes %C Saarbrücken %D 2017 %P 77 p. %V bachelor %9 bachelor
[19]
S. Metzler, S. Günnemann, and P. Miettinen, “Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques,” in 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona, Spain, 2017.
Export
BibTeX
@inproceedings{metzler16hyperbolae, TITLE = {Hyperbolae Are No Hyperbole: {Modelling} Communities That Are Not Cliques}, AUTHOR = {Metzler, Saskia and G{\"u}nnemann, Stephan and Miettinen, Pauli}, LANGUAGE = {eng}, ISBN = {978-1-5090-5473-2}, DOI = {10.1109/ICDM.2016.0044}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {16th IEEE International Conference on Data Mining (ICDM 2016)}, PAGES = {330--339}, ADDRESS = {Barcelona, Spain}, }
Endnote
%0 Conference Proceedings %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-0000-002C-225F-F %R 10.1109/ICDM.2016.0044 %D 2017 %8 02.02.2017 %B 16th International Conference on Data Mining %Z date of event: 2016-12-12 - 2016-12-15 %C Barcelona, Spain %B 16th IEEE International Conference on Data Mining %P 330 - 339 %I IEEE %@ 978-1-5090-5473-2
[20]
A. Mishra and K. Berberich, “How do Order and Proximity Impact the Readability of Event Summaries?,” in Advances in Information Retrieval (ECIR 2017), Aberdeen, Scotland, UK. (Accepted/in press)
Export
BibTeX
@inproceedings{DBLP:conf/ecir/MishraB17, TITLE = {How do Order and Proximity Impact the Readability of Event Summaries?}, AUTHOR = {Mishra, Arunav and Berberich, Klaus}, LANGUAGE = {eng}, PUBLISHER = {Springer}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Information Retrieval (ECIR 2017)}, ADDRESS = {Aberdeen, Scotland, UK}, }
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 How do Order and Proximity Impact the Readability of Event Summaries? : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-20D9-B %D 2016 %8 02.12.2016 %B 39th European Conference on Information Retrieval %Z date of event: 2017-04-09 - 2017-04-13 %C Aberdeen, Scotland, UK %B Advances in Information Retrieval %I Springer
[21]
S. Mukherjee, K. Popat, and G. Weikum, “Exploring Latent Semantic Factors to Find Useful Product Reviews,” in Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), Houston, TX, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{MukherjeeSDM2017, TITLE = {Exploring Latent Semantic Factors to Find Useful Product Reviews}, AUTHOR = {Mukherjee, Subhabrata and Popat, Kashyap and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {SIAM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017)}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Mukherjee, Subhabrata %A Popat, Kashyap %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 Exploring Latent Semantic Factors to Find Useful Product Reviews : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4CD4-6 %D 2017 %B 17th SIAM International Conference on Data Mining %Z date of event: 2017-04-27 - 2017-04-29 %C Houston, TX, USA %B Proceedings of the Seventeenth SIAM International Conference on Data Mining %I SIAM
[22]
S. Neumann, R. Gemulla, and P. Miettinen, “What You Will Gain By Rounding: Theory and Algorithms for Rounding Rank,” in 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona, Spain, 2017.
Export
BibTeX
@inproceedings{neumann16what, TITLE = {What You Will Gain By Rounding: {Theory} and Algorithms for Rounding Rank}, AUTHOR = {Neumann, Stefan and Gemulla, Rainer and Miettinen, Pauli}, LANGUAGE = {eng}, DOI = {10.1109/ICDM.2016.147}, PUBLISHER = {IEEE}, YEAR = {2016}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {16th IEEE International Conference on Data Mining (ICDM 2016)}, EDITOR = {Bonchi, Francesco and Domingo-Ferrer, Josep and Baeza-Yates, Ricardo and Zhou, Zhi-Hua and Wu, Xindong}, PAGES = {380--389}, ADDRESS = {Barcelona, Spain}, }
Endnote
%0 Conference Proceedings %A Neumann, Stefan %A Gemulla, Rainer %A Miettinen, Pauli %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society %T What You Will Gain By Rounding: Theory and Algorithms for Rounding Rank : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-2265-0 %R 10.1109/ICDM.2016.147 %D 2017 %8 02.02.2017 %B 16th International Conference on Data Mining %Z date of event: 2016-12-12 - 2016-12-15 %C Barcelona, Spain %B 16th IEEE International Conference on Data Mining %E Bonchi, Francesco; Domingo-Ferrer, Josep; Baeza-Yates, Ricardo; Zhou, Zhi-Hua; Wu, Xindong %P 380 - 389 %I IEEE
[23]
R. Pienta, M. Kahng, Z. Lin, J. Vreeken, P. Talukdar, J. Abello, G. Parameswaran, and D. H. Chau, “Adaptive Local Exploration of Large Graphs,” in Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017), Houston, TX, USA. (Accepted/in press)
Export
BibTeX
@inproceedings{pienta:17:facets, TITLE = {Adaptive Local Exploration of Large Graphs}, AUTHOR = {Pienta, Robert and Kahng, Minsuk and Lin, Zhang and Vreeken, Jilles and Talukdar, Partha and Abello, James and Parameswaran, Ganesh and Chau, Duen Horng}, LANGUAGE = {eng}, PUBLISHER = {SIAM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Proceedings of the Seventeenth SIAM International Conference on Data Mining (SDM 2017)}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Pienta, Robert %A Kahng, Minsuk %A Lin, Zhang %A Vreeken, Jilles %A Talukdar, Partha %A Abello, James %A Parameswaran, Ganesh %A Chau, Duen Horng %+ External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations %T Adaptive Local Exploration of Large Graphs : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4BEA-D %D 2017 %B 17th SIAM International Conference on Data Mining %Z date of event: 2017-04-27 - 2017-04-29 %C Houston, TX, USA %B Proceedings of the Seventeenth SIAM International Conference on Data Mining %I SIAM
[24]
K. Popat, S. Mukherjee, J. Strötgen, and G. Weikum, “Where the Truth Lies: Explaining the Credibility of Emerging Claims on the Web and Social Media,” in WWW’17, 26th International Conference on World Wide Web, Perth, Australia. (Accepted/in press)
Export
BibTeX
@inproceedings{PopatWWW2017, TITLE = {Where the Truth Lies: {E}xplaining the Credibility of Emerging Claims on the {W}eb and Social Media}, AUTHOR = {Popat, Kashyap and Mukherjee, Subhabrata and Str{\"o}tgen, Jannik and Weikum, Gerhard}, LANGUAGE = {eng}, PUBLISHER = {ACM}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WWW'17, 26th International Conference on World Wide Web}, ADDRESS = {Perth, Australia}, }
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 Where the Truth Lies: Explaining the Credibility of Emerging Claims on the Web and Social Media : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-4CD8-D %D 2017 %B 26th International Conference on World Wide Web %Z date of event: 2017-04-03 - 2017-04-07 %C Perth, Australia %B WWW'17 %I ACM
[25]
N. Reiter, E. Gius, J. Strötgen, and M. Willand, “A Shared Task for a Shared Goal: Systematic Annotation of Literary,” in Digital Humanities 2017 (DH 2017), Montréal, Canada. (Accepted/in press)
Export
BibTeX
@inproceedings{StroetgenDH2017, TITLE = {A Shared Task for a Shared Goal: {S}ystematic Annotation of Literary}, AUTHOR = {Reiter, Nils and Gius, Evelyn and Str{\"o}tgen, Jannik and Willand, Marcus}, LANGUAGE = {eng}, YEAR = {2017}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Digital Humanities 2017 (DH 2017)}, ADDRESS = {Montr{\'e}al, Canada}, }
Endnote
%0 Conference Proceedings %A Reiter, Nils %A Gius, Evelyn %A Strötgen, Jannik %A Willand, Marcus %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T A Shared Task for a Shared Goal: Systematic Annotation of Literary : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-7BDC-3 %D 2017 %B Digital Humanities %Z date of event: 2017-08-08 - 2017-08-11 %C Montréal, Canada %B Digital Humanities 2017
[26]
A. Rohrbach, A. Torabi, M. Rohrbach, N. Tandon, C. Pal, H. Larochelle, A. Courville, and B. Schiele, “Movie Description,” International Journal of Computer Vision, vol. First Online, 2017.
Abstract
Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. In total the Large Scale Movie Description Challenge (LSMDC) contains a parallel corpus of 118,114 sentences and video clips from 202 movies. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are indeed more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in a challenge organized in the context of the workshop "Describing and Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at ICCV 2015.
Export
BibTeX
@article{RohrbachMovie, TITLE = {Movie Description}, AUTHOR = {Rohrbach, Anna and Torabi, Atousa and Rohrbach, Marcus and Tandon, Niket and Pal, Christopher and Larochelle, Hugo and Courville, Aaron and Schiele, Bernt}, LANGUAGE = {eng}, DOI = {10.1007/s11263-016-0987-1}, PUBLISHER = {Springer}, ADDRESS = {London}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. In total the Large Scale Movie Description Challenge (LSMDC) contains a parallel corpus of 118,114 sentences and video clips from 202 movies. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are indeed more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in a challenge organized in the context of the workshop "Describing and Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at ICCV 2015.}, JOURNAL = {International Journal of Computer Vision}, VOLUME = {First Online}, }
Endnote
%0 Journal Article %A Rohrbach, Anna %A Torabi, Atousa %A Rohrbach, Marcus %A Tandon, Niket %A Pal, Christopher %A Larochelle, Hugo %A Courville, Aaron %A Schiele, Bernt %+ Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society %T Movie Description : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002A-FD03-C %R 10.1007/s11263-016-0987-1 %7 2017-01-25 %D 2017 %8 25.01.2017 %X Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. In total the Large Scale Movie Description Challenge (LSMDC) contains a parallel corpus of 118,114 sentences and video clips from 202 movies. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are indeed more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in a challenge organized in the context of the workshop "Describing and Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at ICCV 2015. %K Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Computation and Language, cs.CL %J International Journal of Computer Vision %O IJCV %V First Online %I Springer %C London
[27]
V. Setty, A. Anand, A. Mishra, and A. Anand, “Modeling Event Importance for Ranking Daily News Events,” in WSDM’17, 10th ACM International Conference on Web Search and Data Mining, Cambridge, UK, 2017.
Export
BibTeX
@inproceedings{Setii2017, TITLE = {Modeling Event Importance for Ranking Daily News Events}, AUTHOR = {Setty, Vinay and Anand, Abhijit and Mishra, Arunav and Anand, Avishek}, LANGUAGE = {eng}, ISBN = {978-1-4503-4675-7}, DOI = {10.1145/3018661.3018728}, PUBLISHER = {ACM}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, DATE = {2017}, BOOKTITLE = {WSDM'17, 10th ACM International Conference on Web Search and Data Mining}, PAGES = {231--240}, ADDRESS = {Cambridge, UK}, }
Endnote
%0 Conference Proceedings %A Setty, Vinay %A Anand, Abhijit %A Mishra, Arunav %A Anand, Avishek %+ 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 Modeling Event Importance for Ranking Daily News Events : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-26D5-9 %R 10.1145/3018661.3018728 %D 2017 %B 10th ACM International Conference on Web Search and Data Mining %Z date of event: 2017-02-06 - 2017-02-10 %C Cambridge, UK %B WSDM'17 %P 231 - 240 %I ACM %@ 978-1-4503-4675-7
[28]
C. Teflioudi and R. Gemulla, “Exact and Approximate Maximum Inner Product Search with LEMP,” ACM Transactions on Database Systems, vol. 42, no. 1, 2017.
Export
BibTeX
@article{Teflioudi:2016:EAM:3015779.2996452, TITLE = {Exact and Approximate Maximum Inner Product Search with {LEMP}}, AUTHOR = {Teflioudi, Christina and Gemulla, Rainer}, LANGUAGE = {eng}, ISSN = {0362-5915}, DOI = {10.1145/2996452}, PUBLISHER = {ACM}, ADDRESS = {New York, NY}, YEAR = {2017}, MARGINALMARK = {$\bullet$}, DATE = {2017}, JOURNAL = {ACM Transactions on Database Systems}, VOLUME = {42}, NUMBER = {1}, EID = {5}, }
Endnote
%0 Journal Article %A Teflioudi, Christina %A Gemulla, Rainer %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Exact and Approximate Maximum Inner Product Search with LEMP : %G eng %U http://hdl.handle.net/11858/00-001M-0000-002C-349C-B %R 10.1145/2996452 %7 2016 %D 2017 %J ACM Transactions on Database Systems %O TODS %V 42 %N 1 %Z sequence number: 5 %I ACM %C New York, NY %@ false