An experimental analysis of Noise-Contrastive Estimation: The noise distribution matters

Matthieu Labeau, Alexandre Allauzen

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

Abstract

Noise Contrastive Estimation (NCE) is a learning procedure that is regularly used to train neural language models, since it avoids the computational bottleneck caused by the output softmax. In this paper, we attempt to explain some of the weaknesses of this objective function, and to draw directions for further developments. Experiments on a small task show the issues raised by the unigram noise distribution, and that a context dependent noise distribution, such as the bigram distribution, can solve these issues and provide stable and data-efficient learning.

Original languageEnglish
Title of host publicationShort Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages15-20
Number of pages6
ISBN (Electronic)9781510838604
DOIs
Publication statusPublished - 1 Jan 2017
Event15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
Duration: 3 Apr 20177 Apr 2017

Publication series

Name15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
Volume2

Conference

Conference15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Country/TerritorySpain
CityValencia
Period3/04/177/04/17

Fingerprint

Dive into the research topics of 'An experimental analysis of Noise-Contrastive Estimation: The noise distribution matters'. Together they form a unique fingerprint.

Cite this