Skip to main navigation Skip to search Skip to main content

Improving Word Representation with Word Pair Distributional Asymmetry

  • Beihang University

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

Abstract

Distributed word representation has demonstrated impressive improvements on numerous natural language processing applications. However, most existing word representation learning methods rarely consider use of word order information, and lead to confusion of similarity and relevance. Targeting on this problem we propose a general learning approach DAV (Distributional Asymmetry Vector) to build better word representation by utilizing word pair distributional asymmetry, which contains word order information. Experimental study on two large benchmarks with several state-of-art word representation learning models has shown the potential of the proposed method.

Original languageEnglish
Title of host publicationProceedings - 2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages72-75
Number of pages4
ISBN (Electronic)9781728109749
DOIs
StatePublished - 2 Jul 2018
Event10th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2018 - Zhengzhou, China
Duration: 18 Oct 201820 Oct 2018

Publication series

NameProceedings - 2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2018

Conference

Conference10th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2018
Country/TerritoryChina
CityZhengzhou
Period18/10/1820/10/18

Keywords

  • Distributional asymmetry
  • Word representation

Fingerprint

Dive into the research topics of 'Improving Word Representation with Word Pair Distributional Asymmetry'. Together they form a unique fingerprint.

Cite this