特許機械翻訳の課題解決に向けた機械翻訳技術解説

今村 賢治; 越前谷 博; 江原 暉将; 後藤 功雄; 須藤 克仁; 園尾 聡; 綱川 隆司; 中澤 敏明; 二宮 崇; 王 向莉

doi:10.5715/jnlp.29.925

Survey paper (Peer-Reviewed)

A Survey of Machine Translation Technologies for Machine Translation on Patent Documents

Kenji Imamura, Hiroshi Echizen-ya, Terumasa Ehara, Isao Goto, Katsuhito Sudoh, Satoshi Sonoh, Takashi Tsunakawa, Toshiaki Nakazawa, Takashi Ninomiya, Xiangli Wang

Author information

Kenji Imamura
National Institute of Information and Communication Technologies
Hiroshi Echizen-ya
Hokkai-Gakuen University
Terumasa Ehara
Ehara NLP Research Laboratory
Isao Goto
Japan Broadcasting Corporation
Katsuhito Sudoh
Nara Institute of Science and Technology
Satoshi Sonoh
Toshiba Digital Solutions Corporation
Takashi Tsunakawa
Shizuoka University
Toshiaki Nakazawa
The University of Tokyo
Takashi Ninomiya
Ehime University
Xiangli Wang
Deep Language Co., Ltd.

Keywords: Neural Machine Translation, Patent Translation

JOURNAL FREE ACCESS

2022 Volume 29 Issue 3 Pages 925-985

DOI https://doi.org/10.5715/jnlp.29.925

Details

Abstract

This survey paper reviews machine translation technologies for patent documents. Patent machine translation has been studied for a long time and has evolved by recent neural machine translation. This paper focuses on the following issues with future directions: under- and over translation, consistent technical term translation, long sentence translation, low-resource language pairs, evaluation, efficiency in speed and memory.

Corresponding author

Register with J-STAGE for free!