Ranking entities for web queries through text and knowledge

Schuhmacher, Michael ; Dietz, Laura ; Ponzetto, Simone Paolo

p1461-schuhmacher.pdf - Published

Download (977kB)

DOI: https://doi.org/10.1145/2806416.2806480
URL: https://madoc.bib.uni-mannheim.de/39818
Additional URL: http://dl.acm.org/citation.cfm?id=2806480
URN: urn:nbn:de:bsz:180-madoc-398182
Document Type: Conference or workshop publication
Year of publication: 2015
Book title: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, CIKM 2015, Melbourne, VIC, Australia, October 19 - 23, 2015
Page range: 1461-1470
Date of the conference: October 19-23, 2015
Publisher: Bailey, James
Place of publication: New York, NY [u.a.]
Publishing house: ACM
ISBN: 978-1-4503-3794-6
Publication language: English
Institution: School of Business Informatics and Mathematics > Semantic Web (Juniorprofessur) (Ponzetto 2013-2015)
Subject: 004 Computer science, internet
Abstract: When humans explain complex topics, they naturally talk about involved entities, such as people, locations, or events. In this paper, we aim at automating this process by retrieving and ranking entities that are relevant to understand free-text web-style queries like Argentine British relations, which typically demand a set of heterogeneous entities with no specific target type like, for instance, Falklands-War or Margaret_Thatcher, as answer. Standard approaches to entity retrieval rely purely on features from the knowledge base. We approach the problem from the opposite direction, namely by analyzing web documents that are found to be query-relevant. Our approach hinges on entity linking technology that identifies entity mentions and links them to a knowledge base like Wikipedia. We use a learning-to-rank approach and study different features that use documents, entity mentions, and knowledge base entities – thus bridging document and entity retrieval. Since established bench- marks for this problem do not exist, we use TREC test collections for document ranking and collect custom relevance judgments for entities. Experiments on TREC Robust04 and TREC Web13/14 data show that: i) single entity features, like the frequency of occurrence within the top-ranked documents, or the query retrieval score against a knowledge base, perform generally well; ii) the best overall per- formance is achieved when combining different features that relate an entity to the query, its document mentions, and its knowledge base representation.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item