Skip to main navigation Skip to search Skip to main content

Triangular architecture for rare language translation

  • Shuo Ren
  • , Wenhu Chen
  • , Shujie Liu
  • , Mu Li
  • , Ming Zhou
  • , Shuai Ma
  • Beihang University
  • Beijing Advanced Innovation Center for Big Data and Brain Computing
  • University of California at Santa Barbara
  • Microsoft USA

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

Abstract

Neural Machine Translation (NMT) performs poor on the low-resource language pair (X, Z), especially when Z is a rare language. By introducing another rich language Y , we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data (Y, Z) (may be small) and (X, Y ) (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, Z is taken as the intermediate latent variable, and translation models of Z are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of (X, Y ). Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.

Original languageEnglish
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages56-65
Number of pages10
ISBN (Electronic)9781948087322
DOIs
StatePublished - 2018
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/TerritoryAustralia
CityMelbourne
Period15/07/1820/07/18

Fingerprint

Dive into the research topics of 'Triangular architecture for rare language translation'. Together they form a unique fingerprint.

Cite this