A two level model for context sensitive inference rules

Oren Melamud, Jonathan Berant, Ido Dagan, Jacob Goldberger, Idan Szpektor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

Automatic acquisition of inference rules for predicates has been commonly addressed by computing distributional similarity between vectors of argument words, operating at the word space level. A recent line of work, which addresses context sensitivity of rules, represented contexts in a latent topic space and computed similarity over topic vectors. We propose a novel two-level model, which computes similarities between word-level vectors that are biased by topic-level context representations. Evaluations on a naturallydistributed dataset show that our model significantly outperforms prior word-level and topic-level models. We also release a first context-sensitive inference rule set.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages1331-1340
Number of pages10
ISBN (Print)9781937284503
StatePublished - 2013
Event51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria
Duration: 4 Aug 20139 Aug 2013

Publication series

NameACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Volume1

Conference

Conference51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
Country/TerritoryBulgaria
CitySofia
Period4/08/139/08/13

Fingerprint

Dive into the research topics of 'A two level model for context sensitive inference rules'. Together they form a unique fingerprint.

Cite this