A simple word embedding model for lexical substitution

Oren Melamud, Omer Levy, Ido Dagan

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

Abstract

The lexical substitution task requires identifying meaning-preserving substitutes for a target word instance in a given sentential context. Since its introduction in SemEval-2007, various models addressed this challenge, mostly in an unsupervised setting. In this work we propose a simple model for lexical substitution, which is based on the popular skip-gram word embedding model. The novelty of our approach is in leveraging explicitly the context embeddings generated within the skip-gram model, which were so far considered only as an internal component of the learning process. Our model is efficient, very simple to implement, and at the same time achieves state-of-the-art results on lexical substitution tasks in an unsupervised setting.

Original languageEnglish
Title of host publicationProceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, VS 2015 at the Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, NAACL-HLT 2015
EditorsPhil Blunsom, Shay Cohen, Paramveer Dhillon, Percy Liang
PublisherAssociation for Computational Linguistics (ACL)
Pages1-7
Number of pages7
ISBN (Electronic)9781941643464
DOIs
StatePublished - 2015
Event1st Workshop on Vector Space Modeling for Natural Language Processing, VS 2015 at the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Denver, United States
Duration: 5 Jun 2015 → …

Publication series

Name1st Workshop on Vector Space Modeling for Natural Language Processing, VS 2015 at the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015

Conference

Conference1st Workshop on Vector Space Modeling for Natural Language Processing, VS 2015 at the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015
Country/TerritoryUnited States
CityDenver
Period5/06/15 → …

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'A simple word embedding model for lexical substitution'. Together they form a unique fingerprint.

Cite this