NTT Neural Machine Translation Systems at WAT 2017

Makoto Morishita, Jun Suzuki, Masaaki Nagata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

27 Citations (Scopus)

Abstract

In this year, we participated in four translation subtasks at WAT 2017. Our model structure is quite simple but we used it with well-tuned hyper-parameters, leading to a significant improvement compared to the previous state-of-the-art system. We also tried to make use of the unreliable part of the provided parallel corpus by back-translating and making a synthetic corpus. Our submitted system achieved the new state-of-the-art performance in terms of the BLEU score, as well as human evaluation.

Original languageEnglish
Title of host publicationIJCNLP 2017 - 4th Workshop on Asian Translation, WMT 2017 - Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages89-94
Number of pages6
ISBN (Electronic)9781948087063
Publication statusPublished - 2017
Externally publishedYes
EventIJCNLP 2017 4th Workshop on Asian Translation, WMT 2017 - Taipei, Taiwan, Province of China
Duration: 2017 Nov 272017 Dec 1

Publication series

NameIJCNLP 2017 - 4th Workshop on Asian Translation, WMT 2017 - Proceedings of the Workshop

Conference

ConferenceIJCNLP 2017 4th Workshop on Asian Translation, WMT 2017
Country/TerritoryTaiwan, Province of China
CityTaipei
Period17/11/2717/12/1

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'NTT Neural Machine Translation Systems at WAT 2017'. Together they form a unique fingerprint.

Cite this