Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment

Tu Vu, Vered Shwartz

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

6 Scopus citations

Abstract

Supervised distributional methods are applied successfully in lexical entailment, but recent work questioned whether these methods actually learn a relation between two words. Specifically, Levy et al. (2015) claimed that linear classifiers learn only separate properties of each word. We suggest a cheap and easy way to boost the performance of these methods by integrating multiplicative features into commonly used representations. We provide an extensive evaluation with different classifiers and evaluation setups, and suggest a suitable evaluation setup for the task, eliminating biases existing in previous ones.

Original languageEnglish
Title of host publicationNAACL HLT 2018 - Lexical and Computational Semantics, SEM 2018, Proceedings of the 7th Conference
EditorsMalvina Nissim, Jonathan Berant, Alessandro Lenci
PublisherAssociation for Computational Linguistics (ACL)
Pages160-166
Number of pages7
ISBN (Electronic)9781948087223
StatePublished - 2018
Event7th Joint Conference on Lexical and Computational Semantics, SEM 2018, co-located with NAACL HLT 2018 - New Orleans, United States
Duration: 5 Jun 20186 Jun 2018

Publication series

NameNAACL HLT 2018 - Lexical and Computational Semantics, SEM 2018, Proceedings of the 7th Conference

Conference

Conference7th Joint Conference on Lexical and Computational Semantics, SEM 2018, co-located with NAACL HLT 2018
Country/TerritoryUnited States
CityNew Orleans
Period5/06/186/06/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment'. Together they form a unique fingerprint.

Cite this