• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Multiple resource adaptation for low resource neural machine translation

Research Project

Project/Area Number 17H06822
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeSingle-year Grants
Research Field Intelligent informatics
Research InstitutionOsaka University

Principal Investigator

CHU CHENHUI  大阪大学, データビリティフロンティア機構, 特任助教(常勤) (70784891)

Research Collaborator Dabre Raj  
Project Period (FY) 2017-08-25 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywordsニューラル機械翻訳 / 分野適応 / 低資源 / 機械翻訳 / ローリソース / ドメイン適応 / マルチリソース適応
Outline of Final Research Achievements

In Japan, because of the rapid increase of foreign tourists and the host of the 2020 Tokyo Olympic Games, translation needs are rapidly growing, making machine translation (MT) indispensable. In MT, the translation knowledge is acquired from parallel corpora (sentence-aligned bilingual texts). However, as parallel corpora between Japanese and most languages (e.g., Japanese-Indonesian) and domains (e.g., medical domain) are very scarce (only tens of thousands of parallel sentences or fewer), the translation quality is not satisfied. Improving MT quality in this low-resource scenario is a challenging unsolved problem. Our core idea is adapting knowledge from multiple resources, including parallel corpora of resource rich-languages (such as French-English) and domains (such as the parliamentary domain), and large-scale monolingual web corpora to improve low-resource NMT. Experiments show that we significantly improved low-resource MT with multi-resource adaptation.

Academic Significance and Societal Importance of the Research Achievements

深層学習に基づくニューラル機械翻訳(NMT)の発展により、大規模な対訳コーパスが入手できる場合に最先端の翻訳精度を達成したが、対訳コーパスが少量な場合に翻訳精度が低いことが知られている。しかし、特定言語対や分野の対訳コーパスが大量に存在しない場面が数々ある。例えば、2020年東京オリンピックでは、日本語から東南アジア言語へのスポーツ分野でのMTサービスが非常に重要だと思われるが、それらの言語対や分野において対訳コーパスは少量かほとんど存在しない。本研究で提案したマルチリソース適用はそのような低資源のNMTの翻訳精度向上に成功し、MTの実用化をさらに前進させた。

Report

(3 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Annual Research Report
  • Research Products

    (16 results)

All 2019 2018 2017 Other

All Journal Article (3 results) (of which Peer Reviewed: 3 results,  Open Access: 3 results) Presentation (12 results) (of which Int'l Joint Research: 5 results,  Invited: 1 results) Remarks (1 results)

  • [Journal Article] 統計的機械翻訳のためのRecursive Neural Network による事前並び替えと分析2018

    • Author(s)
      瓦祐希, Chenhui Chu, 荒瀬由紀
    • Journal Title

      自然言語処理

      Volume: 26(1) Pages: 155-178

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] A Comprehensive Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation2018

    • Author(s)
      Chenhui Chu, Raj Dabre and Sadao Kurohashi
    • Journal Title

      情報処理学会論文誌

      Volume: 26

    • NAID

      130007405026

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Constrained Partial Parsing Based Dependency Tree Projection for Tree-to-Tree Machine Translation2017

    • Author(s)
      Chenhui Chu, Yu Shen, Fabien Cromieres and Sadao Kurohashi
    • Journal Title

      Information and Media Technologies

      Volume: 12 Issue: 0 Pages: 172-201

    • DOI

      10.11185/imt.12.172

    • NAID

      130006078764

    • ISSN
      1881-0896
    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] ニューラル機械翻訳における事前並び替えの影響分析2019

    • Author(s)
      瓦祐希, Chenhui Chu, 荒瀬由紀
    • Organizer
      言語処理学会 第25回年次大会, pp.1455-1458
    • Related Report
      2018 Annual Research Report
  • [Presentation] 多国間法律の比較と統計分析のための多言語機械翻訳2019

    • Author(s)
      Chenhui Chu, 梶原 智之, 中島 悠太, 長原 一, 渡辺 理和, 大久保 規子
    • Organizer
      第119回人文科学とコンピュータ研究会発表会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Osaka University MT Systems for WAT 2018: Rewarding, Preordering, and Domain Adaptation2018

    • Author(s)
      Yuki Kawara, Yuto Takebayashi, Chenhui Chu and Yuki Arase
    • Organizer
      In Proceedings of the 5th Workshop on Asian Translation
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Word Rewarding for Adequate Neural Machine Translation2018

    • Author(s)
      Yuto Takebayashi, Chenhui Chu, Yuki Arase and Masaaki Nagata
    • Organizer
      In Proceedings of the 15th International Workshop on Spoken Language Translation, pp. 14-22
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Survey of Domain Adaptation for Neural Machine Translation2018

    • Author(s)
      Chenhui Chu and Rui Wang
    • Organizer
      In Proceedings of the 27th International Conference on Computational Linguistics, pp. 1304-1319
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Recursive Neural Network Based Preordering for English-to-Japanese Machine Translation2018

    • Author(s)
      Yuki Kawara, Chenhui Chu and Yuki Arase
    • Organizer
      In Proceedings of the ACL 2018 Student Research Workshop, pp. 21-27
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ニューラル機械翻訳における分野適応の最先端2018

    • Author(s)
      Chenhui Chu
    • Organizer
      日本通訳翻訳学会第19回年次会
    • Related Report
      2018 Annual Research Report
    • Invited
  • [Presentation] ニューラル機械翻訳における単語予測の重要性について2018

    • Author(s)
      竹林 佑斗, Chenhui Chu, 荒瀬由紀, 永田 昌明
    • Organizer
      2018年度人工知能学会全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Multilingual and Multi-Domain Adaptation for Neural Machine Translation2018

    • Author(s)
      Chenhui Chu and Raj Dabre
    • Organizer
      言語処理学会 第24回年次大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Recursive Neural Networkを用いた事前並び替えによる英日機械翻訳2018

    • Author(s)
      瓦祐希, Chenhui Chu, 荒瀬由紀
    • Organizer
      言語処理学会 第24回年次大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation2017

    • Author(s)
      Chenhui Chu, Raj Dabre and Sadao Kurohashi
    • Organizer
      Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation2017

    • Author(s)
      Chenhui Chu, Raj Dabre and Sadao Kurohashi
    • Organizer
      言語処理学会 第23回年次大会
    • Related Report
      2017 Annual Research Report
  • [Remarks] 研究者個人ホームページ

    • URL

      https://researchmap.jp/chu/

    • Related Report
      2018 Annual Research Report 2017 Annual Research Report

URL: 

Published: 2017-08-25   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi