Spoken-Written Japanese Conversion for Japanese-English University-Lecture Translation

• Nakao Ryota

  Kyoto University

• Chu Chenhui

  Kyoto University

• Kurohashi Sadao

  Kyoto University

Bibliographic Information

Other Title

• 日本語話し言葉書き言葉変換による大学講義の日英翻訳の精度向上

Abstract

In machine translation of spoken language, it is known that phenomena specific to spoken language have a negative impact on translation accuracy. Therefore, in this study, as a preprocessing step for Japanese-English translation in our university lecture translation system, we improve the translation accuracy by automatically converting spoken-style Japanese texts to written-style. First, we create a corpus consisting of Japanese transcriptions of university lectures, their conversions into written language, and the corresponding English texts. Next, we train spoken-written conversion models and Japanese-English translation models using the corpus. As a result, we show that spoken-written Japanese conversion improves the accuracy of Japanese-English translation. In addition, we quantify which phenomena affect translation accuracy and to what extent.

Journal

• Journal of Natural Language Processing

  Journal of Natural Language Processing 28 (4), 1034-1052, 2021

  The Association for Natural Language Processing

Keywords

• Machine Translation
• Spoken Language
• Written Language
• Lecture Translation

Details

• CRID: 1390008918660947840
• NII Article ID: 130008129491
• DOI: 10.5715/jnlp.28.1034
• ISSN: 21858314
• ISSN: 13407619
• HANDLE: 2433/276891
• Web Site: https://www.jstage.jst.go.jp/article/jnlp/28/4/28_1034/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • IRDB
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed