Investigating backtranslation in neural machine translation

Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette De Buy Wenniger, Peyman Passban

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

12 Citations (Scopus)

Abstract

A prerequisite for training corpus-based machine translation (MT) systems – either Statistical MT (SMT) or Neural MT (NMT) – is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT. Recently researchers have shown that back-translating monolingual data can be used to create synthetic parallel corpora, which in turn can be used in combination with authentic parallel data to train a high-quality NMT system. Given that large collections of new parallel text become available only quite rarely, backtranslation has become the norm when building state-of-the-art NMT systems, especially in resource-poor scenarios. However, we assert that there are many unknown factors regarding the actual effects of back-translated data on the translation capabilities of an NMT model. Accordingly, in this work we investigate how using back-translated data as a training corpus – both as a separate standalone dataset as well as combined with human-generated parallel data – affects the performance of an NMT model. We use incrementally larger amounts of back-translated data to train a range of NMT systems for German-to-English, and analyse the resulting translation performance.

Original languageEnglish
Title of host publicationEAMT 2018 - Proceedings of the 21st Annual Conference of the European Association for Machine Translation
EditorsJuan Antonio Perez-Ortiz, Felipe Sanchez-Martinez, Miquel Espla-Gomis, Maja Popovic, Celia Rico, Andre Martins, Joachim Van den Bogaert, Mikel L. Forcada
PublisherEuropean Association for Machine Translation
Pages249-258
Number of pages10
ISBN (Electronic)9788409019014
Publication statusPublished - 2018
Externally publishedYes
Event21st Annual Conference of the European Association for Machine Translation, EAMT 2018 - Alacant, Spain
Duration: 28 May 201830 May 2018

Publication series

NameEAMT 2018 - Proceedings of the 21st Annual Conference of the European Association for Machine Translation

Conference

Conference21st Annual Conference of the European Association for Machine Translation, EAMT 2018
CountrySpain
CityAlacant
Period28/05/1830/05/18

Fingerprint Dive into the research topics of 'Investigating backtranslation in neural machine translation'. Together they form a unique fingerprint.

  • Cite this

    Poncelas, A., Shterionov, D., Way, A., De Buy Wenniger, G. M., & Passban, P. (2018). Investigating backtranslation in neural machine translation. In J. A. Perez-Ortiz, F. Sanchez-Martinez, M. Espla-Gomis, M. Popovic, C. Rico, A. Martins, J. Van den Bogaert, & M. L. Forcada (Eds.), EAMT 2018 - Proceedings of the 21st Annual Conference of the European Association for Machine Translation (pp. 249-258). (EAMT 2018 - Proceedings of the 21st Annual Conference of the European Association for Machine Translation). European Association for Machine Translation.