Learning entailment rules for unary templates

Idan Szpektor, Ido Dagan

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

82 Scopus citations

Abstract

Most work on unsupervised entailment rule acquisition focused on rules between templates with two variables, ignoring unary rules - entailment rules between templates with a single variable. In this paper we investigate two approaches for unsupervised learning of such rules and compare the proposed methods with a binary rule learning method. The results show that the learned unary rule-sets outperform the binary rule-set. In addition, a novel directional similarity measure for learning entailment, termed Balanced-Inclusion, is the best performing measure.

Original languageEnglish
Title of host publicationColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages849-856
Number of pages8
ISBN (Print)9781905593446
DOIs
StatePublished - 2008
Event22nd International Conference on Computational Linguistics, Coling 2008 - Manchester, United Kingdom
Duration: 18 Aug 200822 Aug 2008

Publication series

NameColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
Volume1

Conference

Conference22nd International Conference on Computational Linguistics, Coling 2008
Country/TerritoryUnited Kingdom
CityManchester
Period18/08/0822/08/08

Fingerprint

Dive into the research topics of 'Learning entailment rules for unary templates'. Together they form a unique fingerprint.

Cite this