Lexical inference over multi-word predicates: A distributional approach

Omri Abend, Shay B. Cohen, Mark Steedman

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

2 Scopus citations

Abstract

Representing predicates in terms of their argument distribution is common practice in NLP. Multi-word predicates (MWPs) in this context are often either disregarded or considered as fixed expressions. The latter treatment is unsatisfactory in two ways: (1) identifying MWPs is notoriously difficult, (2) MWPs show varying degrees of compositionality and could benefit from taking into account the identity of their component parts. We propose a novel approach that integrates the distributional representation of multiple sub-sets of the MWP's words. We assume a latent distribution over sub-sets of the MWP, and estimate it relative to a downstream prediction task. Focusing on the supervised identification of lexical inference relations, we compare against state-of-the-art baselines that consider a single sub-set of an MWP, obtaining substantial improvements. To our knowledge, this is the first work to address lexical relations between MWPs of varying degrees of compositionality within distributional semantics.

Original languageAmerican English
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages644-654
Number of pages11
ISBN (Print)9781937284725
DOIs
StatePublished - 2014
Externally publishedYes
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: 22 Jun 201427 Jun 2014

Publication series

Name52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference
Volume1

Conference

Conference52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
Country/TerritoryUnited States
CityBaltimore, MD
Period22/06/1427/06/14

Fingerprint

Dive into the research topics of 'Lexical inference over multi-word predicates: A distributional approach'. Together they form a unique fingerprint.

Cite this