2020
[1]
H. Arnaout, S. Razniewski, and G. Weikum, “Negative Statements Considered Useful,” 2020. [Online]. Available: http://arxiv.org/abs/2001.04425. (arXiv: 2001.04425)
Abstract
Knowledge bases (KBs), pragmatic collections of knowledge about notable entities, are an important asset in applications such as search, question answering and dialogue. Rooted in a long tradition in knowledge representation, all popular KBs only store positive information, while they abstain from taking any stance towards statements not contained in them. In this paper, we make the case for explicitly stating interesting statements which are not true. Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking. We introduce two approaches towards compiling negative statements. (i) In peer-based statistical inferences, we compare entities with highly related entities in order to derive potential negative statements, which we then rank using supervised and unsupervised features. (ii) In query-log-based text extraction, we use a pattern-based approach for harvesting search engine query logs. Experimental results show that both approaches hold promising and complementary potential. Along with this paper, we publish the first datasets on interesting negative information, containing over 1.1M statements for 100K popular Wikidata entities.
Export
BibTeX
@online{Arnaout_arXiv2001.04425, TITLE = {Negative Statements Considered Useful}, AUTHOR = {Arnaout, Hiba and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/2001.04425}, EPRINT = {2001.04425}, EPRINTTYPE = {arXiv}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Knowledge bases (KBs), pragmatic collections of knowledge about notable entities, are an important asset in applications such as search, question answering and dialogue. Rooted in a long tradition in knowledge representation, all popular KBs only store positive information, while they abstain from taking any stance towards statements not contained in them. In this paper, we make the case for explicitly stating interesting statements which are not true. Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking. We introduce two approaches towards compiling negative statements. (i) In peer-based statistical inferences, we compare entities with highly related entities in order to derive potential negative statements, which we then rank using supervised and unsupervised features. (ii) In query-log-based text extraction, we use a pattern-based approach for harvesting search engine query logs. Experimental results show that both approaches hold promising and complementary potential. Along with this paper, we publish the first datasets on interesting negative information, containing over 1.1M statements for 100K popular Wikidata entities.}, }
Endnote
%0 Report %A Arnaout, Hiba %A Razniewski, Simon %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 Negative Statements Considered Useful : %G eng %U http://hdl.handle.net/21.11116/0000-0005-821F-6 %U http://arxiv.org/abs/2001.04425 %D 2020 %X Knowledge bases (KBs), pragmatic collections of knowledge about notable entities, are an important asset in applications such as search, question answering and dialogue. Rooted in a long tradition in knowledge representation, all popular KBs only store positive information, while they abstain from taking any stance towards statements not contained in them. In this paper, we make the case for explicitly stating interesting statements which are not true. Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking. We introduce two approaches towards compiling negative statements. (i) In peer-based statistical inferences, we compare entities with highly related entities in order to derive potential negative statements, which we then rank using supervised and unsupervised features. (ii) In query-log-based text extraction, we use a pattern-based approach for harvesting search engine query logs. Experimental results show that both approaches hold promising and complementary potential. Along with this paper, we publish the first datasets on interesting negative information, containing over 1.1M statements for 100K popular Wikidata entities. %K Computer Science, Information Retrieval, cs.IR,Computer Science, Artificial Intelligence, cs.AI,Computer Science, Computation and Language, cs.CL,Computer Science, Databases, cs.DB
[2]
Y. Chalier, S. Razniewski, and G. Weikum, “Joint Reasoning for Multi-Faceted Commonsense Knowledge,” 2020. [Online]. Available: http://arxiv.org/abs/2001.04170. (arXiv: 2001.04170)
Abstract
Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept. Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid. This paper aims to overcome these limitations by introducing a multi-faceted model of CSK statements and methods for joint reasoning over sets of inter-related statements. Our model captures four different dimensions of CSK statements: plausibility, typicality, remarkability and salience, with scoring and ranking along each dimension. For example, hyenas drinking water is typical but not salient, whereas hyenas eating carcasses is salient. For reasoning and ranking, we develop a method with soft constraints, to couple the inference over concepts that are related in in a taxonomic hierarchy. The reasoning is cast into an integer linear programming (ILP), and we leverage the theory of reduction costs of a relaxed LP to compute informative rankings. This methodology is applied to several large CSK collections. Our evaluation shows that we can consolidate these inputs into much cleaner and more expressive knowledge. Results are available at https://dice.mpi-inf.mpg.de.
Export
BibTeX
@online{Chalier_arXiv2001.04170, TITLE = {Joint Reasoning for Multi-Faceted Commonsense Knowledge}, AUTHOR = {Chalier, Yohan and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/2001.04170}, EPRINT = {2001.04170}, EPRINTTYPE = {arXiv}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept. Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid. This paper aims to overcome these limitations by introducing a multi-faceted model of CSK statements and methods for joint reasoning over sets of inter-related statements. Our model captures four different dimensions of CSK statements: plausibility, typicality, remarkability and salience, with scoring and ranking along each dimension. For example, hyenas drinking water is typical but not salient, whereas hyenas eating carcasses is salient. For reasoning and ranking, we develop a method with soft constraints, to couple the inference over concepts that are related in in a taxonomic hierarchy. The reasoning is cast into an integer linear programming (ILP), and we leverage the theory of reduction costs of a relaxed LP to compute informative rankings. This methodology is applied to several large CSK collections. Our evaluation shows that we can consolidate these inputs into much cleaner and more expressive knowledge. Results are available at https://dice.mpi-inf.mpg.de.}, }
Endnote
%0 Report %A Chalier, Yohan %A Razniewski, Simon %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 %T Joint Reasoning for Multi-Faceted Commonsense Knowledge : %G eng %U http://hdl.handle.net/21.11116/0000-0005-8226-D %U http://arxiv.org/abs/2001.04170 %D 2020 %X Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept. Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid. This paper aims to overcome these limitations by introducing a multi-faceted model of CSK statements and methods for joint reasoning over sets of inter-related statements. Our model captures four different dimensions of CSK statements: plausibility, typicality, remarkability and salience, with scoring and ranking along each dimension. For example, hyenas drinking water is typical but not salient, whereas hyenas eating carcasses is salient. For reasoning and ranking, we develop a method with soft constraints, to couple the inference over concepts that are related in in a taxonomic hierarchy. The reasoning is cast into an integer linear programming (ILP), and we leverage the theory of reduction costs of a relaxed LP to compute informative rankings. This methodology is applied to several large CSK collections. Our evaluation shows that we can consolidate these inputs into much cleaner and more expressive knowledge. Results are available at https://dice.mpi-inf.mpg.de. %K Computer Science, Computation and Language, cs.CL,Computer Science, Artificial Intelligence, cs.AI,Computer Science, Information Retrieval, cs.IR
[3]
C. X. Chu, S. Razniewski, and G. Weikum, “ENTYFI: Entity Typing in Fictional Texts,” in WSDM’19, 13th International Conference on Web Search and Data Mining, Houston, TX, USA, 2020.
Export
BibTeX
@inproceedings{ChuWSDM2020, TITLE = {{ENTYFI}: {E}ntity Typing in Fictional Texts}, AUTHOR = {Chu, Cuong Xuan and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {9781450368223}, DOI = {10.1145/3336191.3371808}, PUBLISHER = {ACM}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WSDM'19, 13th International Conference on Web Search and Data Mining}, EDITOR = {Caverlee, James and Hu, Xia Ben}, PAGES = {124--132}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Chu, Cuong Xuan %A Razniewski, Simon %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 ENTYFI: Entity Typing in Fictional Texts : %G eng %U http://hdl.handle.net/21.11116/0000-0006-A27E-6 %R 10.1145/3336191.3371808 %D 2020 %B 13th International Conference on Web Search and Data Mining %Z date of event: 2020-02-03 - 2020-02-07 %C Houston, TX, USA %B WSDM'19 %E Caverlee, James; Hu, Xia Ben %P 124 - 132 %I ACM %@ 9781450368223
[4]
F. Darari, W. Nutt, S. Razniewski, and S. Rudolph, “Completeness and soundness guarantees for conjunctive SPARQL queries over RDF data sources with completeness statements,” Semantic Web, vol. 11, no. 1, 2020.
Export
BibTeX
@article{Darari2020, TITLE = {Completeness and soundness guarantees for conjunctive {SPARQL} queries over {RDF} data sources with completeness statements}, AUTHOR = {Darari, Fariza and Nutt, Werner and Razniewski, Simon and Rudolph, Sebastian}, LANGUAGE = {eng}, ISSN = {1570-0844}, DOI = {10.3233/SW-190344}, PUBLISHER = {IOS Press}, ADDRESS = {Amsterdam}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, DATE = {2020}, JOURNAL = {Semantic Web}, VOLUME = {11}, NUMBER = {1}, PAGES = {441--482}, }
Endnote
%0 Journal Article %A Darari, Fariza %A Nutt, Werner %A Razniewski, Simon %A Rudolph, Sebastian %+ External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Completeness and soundness guarantees for conjunctive SPARQL queries over RDF data sources with completeness statements : %G eng %U http://hdl.handle.net/21.11116/0000-0006-9A06-6 %R 10.3233/SW-190344 %7 2020 %D 2020 %J Semantic Web %V 11 %N 1 %& 441 %P 441 - 482 %I IOS Press %C Amsterdam %@ false
[5]
S. Ghosh, S. Razniewski, and G. Weikum, “Uncovering Hidden Semantics of Set Information in Knowledge Bases,” 2020. [Online]. Available: http://arxiv.org/abs/2003.03155. (arXiv: 2003.03155)
Abstract
Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often represented in two formats: (i) via counting predicates such as numberOfChildren and staffSize, that store aggregated integers, and (ii) via enumerating predicates such as parentOf and worksFor, that store individual set memberships. Both formats are typically complementary: unlike enumerating predicates, counting predicates do not give away individuals, but are more likely informative towards the true set size, thus this coexistence could enable interesting applications in question answering and KB curation. In this paper we aim at uncovering this hidden knowledge. We proceed in two steps. (i) We identify set-valued predicates from a given KB predicates via statistical and embedding-based features. (ii) We link counting predicates and enumerating predicates by a combination of co-occurrence, correlation and textual relatedness metrics. We analyze the prevalence of count information in four prominent knowledge bases, and show that our linking method achieves up to 0.55 F1 score in set predicate identification versus 0.40 F1 score of a random selection, and normalized discounted gains of up to 0.84 at position 1 and 0.75 at position 3 in relevant predicate alignments. Our predicate alignments are showcased in a demonstration system available at https://counqer.mpi-inf.mpg.de/spo.
Export
BibTeX
@online{Ghosh_arXiv2003.03155, TITLE = {Uncovering Hidden Semantics of Set Information in Knowledge Bases}, AUTHOR = {Ghosh, Shrestha and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, URL = {http://arxiv.org/abs/2003.03155}, EPRINT = {2003.03155}, EPRINTTYPE = {arXiv}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, ABSTRACT = {Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often represented in two formats: (i) via counting predicates such as numberOfChildren and staffSize, that store aggregated integers, and (ii) via enumerating predicates such as parentOf and worksFor, that store individual set memberships. Both formats are typically complementary: unlike enumerating predicates, counting predicates do not give away individuals, but are more likely informative towards the true set size, thus this coexistence could enable interesting applications in question answering and KB curation. In this paper we aim at uncovering this hidden knowledge. We proceed in two steps. (i) We identify set-valued predicates from a given KB predicates via statistical and embedding-based features. (ii) We link counting predicates and enumerating predicates by a combination of co-occurrence, correlation and textual relatedness metrics. We analyze the prevalence of count information in four prominent knowledge bases, and show that our linking method achieves up to 0.55 F1 score in set predicate identification versus 0.40 F1 score of a random selection, and normalized discounted gains of up to 0.84 at position 1 and 0.75 at position 3 in relevant predicate alignments. Our predicate alignments are showcased in a demonstration system available at https://counqer.mpi-inf.mpg.de/spo.}, }
Endnote
%0 Report %A Ghosh, Shrestha %A Razniewski, Simon %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 Uncovering Hidden Semantics of Set Information in Knowledge Bases : %G eng %U http://hdl.handle.net/21.11116/0000-0007-0662-4 %U http://arxiv.org/abs/2003.03155 %D 2020 %X Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often represented in two formats: (i) via counting predicates such as numberOfChildren and staffSize, that store aggregated integers, and (ii) via enumerating predicates such as parentOf and worksFor, that store individual set memberships. Both formats are typically complementary: unlike enumerating predicates, counting predicates do not give away individuals, but are more likely informative towards the true set size, thus this coexistence could enable interesting applications in question answering and KB curation. In this paper we aim at uncovering this hidden knowledge. We proceed in two steps. (i) We identify set-valued predicates from a given KB predicates via statistical and embedding-based features. (ii) We link counting predicates and enumerating predicates by a combination of co-occurrence, correlation and textual relatedness metrics. We analyze the prevalence of count information in four prominent knowledge bases, and show that our linking method achieves up to 0.55 F1 score in set predicate identification versus 0.40 F1 score of a random selection, and normalized discounted gains of up to 0.84 at position 1 and 0.75 at position 3 in relevant predicate alignments. Our predicate alignments are showcased in a demonstration system available at https://counqer.mpi-inf.mpg.de/spo. %K Computer Science, Databases, cs.DB,Computer Science, Information Retrieval, cs.IR
[6]
S. Ghosh, S. Razniewski, and G. Weikum, “Uncovering Hidden Semantics of Set Information in Knowledge Bases,” Journal of Web Semantics, vol. 64, 2020.
Export
BibTeX
@article{Ghosh_2020, TITLE = {Uncovering Hidden Semantics of Set Information in Knowledge Bases}, AUTHOR = {Ghosh, Shrestha and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, ISSN = {1570-8268}, DOI = {10.1016/j.websem.2020.100588}, PUBLISHER = {Elsevier}, ADDRESS = {Amsterdam}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, DATE = {2020}, JOURNAL = {Journal of Web Semantics}, VOLUME = {64}, EID = {100588}, }
Endnote
%0 Journal Article %A Ghosh, Shrestha %A Razniewski, Simon %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 Uncovering Hidden Semantics of Set Information in Knowledge Bases : %G eng %U http://hdl.handle.net/21.11116/0000-0007-066D-9 %R 10.1016/j.websem.2020.100588 %7 2020 %D 2020 %J Journal of Web Semantics %V 64 %Z sequence number: 100588 %I Elsevier %C Amsterdam %@ false
[7]
V. T. Ho, K. Pal, N. Kleer, K. Berberich, and G. Weikum, “Entities with Quantities: Extraction, Search, and Ranking,” in WSDM’19, 13th International Conference on Web Search and Data Mining, Houston, TX, USA, 2020.
Export
BibTeX
@inproceedings{HoWSDM2020, TITLE = {Entities with Quantities: {E}xtraction, Search, and Ranking}, AUTHOR = {Ho, Vinh Thinh and Pal, Koninika and Kleer, Niko and Berberich, Klaus and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {9781450368223}, DOI = {10.1145/3336191.3371860}, PUBLISHER = {ACM}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WSDM'19, 13th International Conference on Web Search and Data Mining}, EDITOR = {Caverlee, James and Hu, Xia Ben}, PAGES = {833--836}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Ho, Vinh Thinh %A Pal, Koninika %A Kleer, Niko %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 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 Entities with Quantities: Extraction, Search, and Ranking : %G eng %U http://hdl.handle.net/21.11116/0000-0006-A284-D %R 10.1145/3336191.3371860 %D 2020 %B 13th International Conference on Web Search and Data Mining %Z date of event: 2020-02-03 - 2020-02-07 %C Houston, TX, USA %B WSDM'19 %E Caverlee, James; Hu, Xia Ben %P 833 - 836 %I ACM %@ 9781450368223
[8]
P. Mandros, M. Boley, and J. Vreeken, “Discovering Dependencies with Reliable Mutual Information,” Knowledge and Information Systems, 2020.
Export
BibTeX
@article{Mandros2020, TITLE = {Discovering Dependencies with Reliable Mutual Information}, AUTHOR = {Mandros, Panagiotis and Boley, Mario and Vreeken, Jilles}, LANGUAGE = {eng}, ISSN = {0219-3116}, DOI = {10.1007/s10115-020-01494-9}, PUBLISHER = {Springer}, ADDRESS = {New York, NY}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, JOURNAL = {Knowledge and Information Systems}, }
Endnote
%0 Journal Article %A Mandros, Panagiotis %A Boley, Mario %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 Discovering Dependencies with Reliable Mutual Information : %G eng %U http://hdl.handle.net/21.11116/0000-0006-DC90-F %R 10.1007/s10115-020-01494-9 %7 2020 %D 2020 %J Knowledge and Information Systems %I Springer %C New York, NY %@ false
[9]
S. Nag Chowdhury, W. Cheng, G. de Melo, S. Razniewski, and G. Weikum, “Illustrate Your Story: Enriching Text with Images,” in WSDM’19, 13th International Conference on Web Search and Data Mining, Houston, TX, USA, 2020.
Export
BibTeX
@inproceedings{NagWSDM2020, TITLE = {Illustrate Your Story: {Enriching} Text with Images}, AUTHOR = {Nag Chowdhury, Sreyasi and Cheng, William and de Melo, Gerard and Razniewski, Simon and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {9781450368223}, DOI = {10.1145/3336191.3371866}, PUBLISHER = {ACM}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WSDM'19, 13th International Conference on Web Search and Data Mining}, EDITOR = {Caverlee, James and Hu, Xia Ben}, PAGES = {849--852}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Nag Chowdhury, Sreyasi %A Cheng, William %A de Melo, Gerard %A Razniewski, Simon %A Weikum, Gerhard %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society Databases and Information Systems, MPI for Informatics, Max Planck Society %T Illustrate Your Story: Enriching Text with Images : %G eng %U http://hdl.handle.net/21.11116/0000-0006-A27C-8 %R 10.1145/3336191.3371866 %D 2020 %B 13th International Conference on Web Search and Data Mining %Z date of event: 2020-02-03 - 2020-02-07 %C Houston, TX, USA %B WSDM'19 %E Caverlee, James; Hu, Xia Ben %P 849 - 852 %I ACM %@ 9781450368223
[10]
V. Sathya, S. Ghosh, A. Ramamurthy, and B. R. Tamma, “Small Cell Planning: Resource Management and Interference Mitigation Mechanisms in LTE HetNets,” Wireless Personal Communications, 2020.
Export
BibTeX
@article{Sathya2020, TITLE = {Small Cell Planning: {R}esource Management and Interference Mitigation Mechanisms in {LTE HetNets}}, AUTHOR = {Sathya, Vanlin and Ghosh, Shrestha and Ramamurthy, Arun and Tamma, Bheemarjuna Reddy}, LANGUAGE = {eng}, ISSN = {0929-6212}, DOI = {10.1007/s11277-020-07574-x}, PUBLISHER = {Springer}, ADDRESS = {New York, NY}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, JOURNAL = {Wireless Personal Communications}, }
Endnote
%0 Journal Article %A Sathya, Vanlin %A Ghosh, Shrestha %A Ramamurthy, Arun %A Tamma, Bheemarjuna Reddy %+ External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations %T Small Cell Planning: Resource Management and Interference Mitigation Mechanisms in LTE HetNets : %G eng %U http://hdl.handle.net/21.11116/0000-0006-B963-A %R 10.1007/s11277-020-07574-x %7 2020 %D 2020 %J Wireless Personal Communications %I Springer %C New York, NY %@ false
[11]
E. Terolli, P. Ernst, and G. Weikum, “Focused Query Expansion with Entity Cores for Patient-Centric Health Search,” in The Semantic Web -- ISWC 2020, Athens, Greece (Virtual Conference), 2020.
Export
BibTeX
@inproceedings{Terolli_ISWC2020, TITLE = {Focused Query Expansion with Entity Cores for Patient-Centric Health Search}, AUTHOR = {Terolli, Erisa and Ernst, Patrick and Weikum, Gerhard}, LANGUAGE = {eng}, ISBN = {978-3-030-62418-7}, DOI = {10.1007/978-3-030-62419-4_31}, PUBLISHER = {Springer}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, DATE = {2020}, BOOKTITLE = {The Semantic Web -- ISWC 2020}, EDITOR = {Pan, Jeff Z. and Tamma, Valentina and D'Amato, Claudia and Janowicz, Krzysztof and Fu, Bo and Polleres, Axel and Seneviratne, Oshani and Kagal, Lalana}, PAGES = {547--564}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {12506}, ADDRESS = {Athens, Greece (Virtual Conference)}, }
Endnote
%0 Conference Proceedings %A Terolli, Erisa %A Ernst, Patrick %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 Focused Query Expansion with Entity Cores for Patient-Centric Health Search : %G eng %U http://hdl.handle.net/21.11116/0000-0007-78D7-0 %R 10.1007/978-3-030-62419-4_31 %D 2020 %B 19th International Semantic Web Conference %Z date of event: 2020-11-02 - 2020-11-06 %C Athens, Greece (Virtual Conference) %B The Semantic Web -- ISWC 2020 %E Pan, Jeff Z.; Tamma, Valentina; D'Amato, Claudia; Janowicz, Krzysztof; Fu, Bo; Polleres, Axel; Seneviratne, Oshani; Kagal, Lalana %P 547 - 564 %I Springer %@ 978-3-030-62418-7 %B Lecture Notes in Computer Science %N 12506
[12]
A. Yates, S. Arora, X. Zhang, W. Yang, K. M. Jose, and J. Lin, “Capreolus: A Toolkit for End-to-End Neural Ad Hoc Retrieval,” in WSDM’19, 13th International Conference on Web Search and Data Mining, Houston, TX, USA, 2020.
Export
BibTeX
@inproceedings{YatesWSDM2020, TITLE = {Capreolus: {A} Toolkit for End-to-End Neural Ad Hoc Retrieval}, AUTHOR = {Yates, Andrew and Arora, Siddhant and Zhang, Xinyu and Yang, Wei and Jose, Kevin Martin and Lin, Jimmy}, LANGUAGE = {eng}, ISBN = {9781450368223}, DOI = {10.1145/3336191.3371868}, PUBLISHER = {ACM}, YEAR = {2020}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {WSDM'19, 13th International Conference on Web Search and Data Mining}, EDITOR = {Caverlee, James and Hu, Xia Ben}, PAGES = {861--864}, ADDRESS = {Houston, TX, USA}, }
Endnote
%0 Conference Proceedings %A Yates, Andrew %A Arora, Siddhant %A Zhang, Xinyu %A Yang, Wei %A Jose, Kevin Martin %A Lin, Jimmy %+ Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations Databases and Information Systems, MPI for Informatics, Max Planck Society External Organizations %T Capreolus: A Toolkit for End-to-End Neural Ad Hoc Retrieval : %G eng %U http://hdl.handle.net/21.11116/0000-0006-A28E-3 %R 10.1145/3336191.3371868 %D 2020 %B 13th International Conference on Web Search and Data Mining %Z date of event: 2020-02-03 - 2020-02-07 %C Houston, TX, USA %B WSDM'19 %E Caverlee, James; Hu, Xia Ben %P 861 - 864 %I ACM %@ 9781450368223