ASTREC

NICT

先進的翻訳技術研究室

【学術論文】

  • 今村　賢治, 隅田　英一郎. 事前訓練モデルの言語拡張とその効果. 一般社団法人日本特許情報機構　JAPIO YEAR BOOK 2021, pp.302-305, November 2021.

【国際会議・ワークショップ】

  • Mayuka Yamamoto, Masaru Yamada, Atsushi Fujita , Rei Miyata, Kyo Kageura. Designing a Metalanguage of Translation Strategies for Translation Training: Demystifying the Art of Translation. In Proceedings of the 7th International Conference of International Association for Translation and Intercultural Studies (IATIS), page. 294, September 2021.
  • Atsushi Fujita. Attainable Text-to-Text Machine Translation vs. Translation: Issues Beyond Linguistic Processing. In Proceedings of the 18th biennial Machine Translation Summit (MT Summit XVIII), pages 215-230, August 16-20, 2021.
  • Raj Dabre and Atsushi Fujita. Investigating SoftMax Tempering for Training Neural Machine Translation Models. In Proceedings of the 18th biennial Machine Translation Summit (MT Summit XVIII), pages 114-126, August 16-20, 2021.
  • Raj Dabre, Aizhan Imankulova, and Masahiro Kaneko. Studying the Impact of Document-level Context on Simultaneous Neural Machine Translation. In Proceedings of the 18th biennial Machine Translation Summit (MT Summit XVIII), pages 202-214, August 16-20, 2021.
  • Keiji Yasuda, Ichiro Yamada, Naoaki Okazaki, Hideki Tanaka, Hidehiro Asaka, Takeshi Anzai, and Fumiaki Sugaya. Field Experiments of Real-Time Foreign News Distribution Powered by MT. In Proceedings of the 18th biennial Machine Translation Summit (MT Summit XVIII), August 16-20, 2021.
  • 今村　賢治, 隅田英一郎. NICT-2 Translation System at WAT-2021: Applying a Pretrained Multilingual Encoder-Decoder Model to Low-resource Language Pairs. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 90-95, August 6, 2021.
  • 中澤　敏明, 中山　英樹, 丁　塵辰, Raj Dabre, 東山　翔平, 美野 秀弥, 後藤 功男, Win Pa Pa, Anoop Kunchukuttan, Shantipiriya Parida, Ondrej Bojar, Chenhui Chu, Akiko Eriguchi, Kaori Abe, Yusuke Oda, 黒橋 禎夫. Overview of the 8th Workshop on Asian Translation. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), August 6, 2021.
  • Raj Dabre and Abhisek Chakrabarty. NICT-5’s Submission to WAT 2021: MBART Pre-training and In-Domain Fine Tuning for Indic Languages. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 198-204, August 6, 2021.
  • Benjamin Marie, Atsushi Fujita and Raphael Rubino. Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers. In Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), pages 7297-7306, August 1-6, 2021.
  • Benjamin Marie and Atsushi Fujita. Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation. In Proceedings of The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), August 1-6, 2021.
  • Zuchao Li, Masao Utiyama, Eiichiro Sumita and Hai Zhao. NICT’s Neural Machine Translation Systems for the WAT21 Restricted Translation Task. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), August 1-6, 2021.
  • Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita and Tiejun Zhao. Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL2021), June 6-11, 2021.
  • Shohei Higashiyama, Masao Utiyama, Taro Watanabe, and Eiishiro Sumita. User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL2021), Mexico City, Mexico, pages 5532-5541, June 6-11, 2021.
  • Rei Miyata and Atsushi Fujita. Understanding Pre-Editing for Black-Box Neural Machine Translation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Kiev, Ukraine, pages 1539-1550, April 21-23, 2021.

【国内会議・研究会】

  • 山本　真佑花, 山田　優, 藤田　篤. 翻訳学習者による英日翻訳方略の学習可能性. 日本通訳翻訳学会第22回年次大会, September 2021.
  • 今村　賢治．知識蒸留によるニューラル機械翻訳の高速化検討．言語処理学会第27回年次大会発表論文集，pp.123-127，March 15-19，2021．
  • Marie Benjamin，藤田　篤．Altering Parallel Data into User-Generated Texts with Zero-Shot Neural Machine Translation．言語処理学会第27回年次大会発表論文集，pp.128-132, March 15-19, 2021．
  • 西野 竜太郎，新田 順也，山本 真佑花，藤田 篤，大西 菜奈美，山田 優．翻訳の主観評価で用いられる表現．言語処理学会第27回年次大会発表論文集，pp.919-923，March 15-19，2021．
  • 山本 真佑花，山田　優，藤田　篤，宮田　玲，影浦 峡．メタ言語としての翻訳方略体系の構築と検証．言語処理学会第27回年次大会発表論文集，pp.1111-1116．March 15-19，2021．
  • 坂井 優介，渡辺 太郎，藤田 篤．知識グラフ埋め込みを用いたニューラル機械翻訳におけるエンティティ表現の改良．言語処理学会第27回年次大会発表論文集，pp.1386-1390，March 15-19，2021．
  • 西原 大貴，梶原 智之，荒瀬 由紀，藤田 篤．言い換えラティスを用いたテキスト生成の性能改善． 言語処理学会第27回年次大会発表論文集．pp.1729-1733，March 15-19，2021．
  • 藤田　篤. 翻訳時に必要な情報を参照しない機械翻訳が生じる問題. 日本通訳翻訳学会関東支部第60回例会, June 5, 2021.

【プレプリント】

  • Zhuosheng Zhang, Siru Ouyang, Hai Zhao, Masao Utiyama and Eiichiro Sumita. Smoothing Dialogue States for Open Conversational Machine Reading. arXiv:2108.12599 [cs.CL]. August 28, 2021.
  • Raj Dabre and Eiichiro Sumita. YANMTT: Yet Another Neural Machine Translation Toolkit. arXiv:2108.11126 [cs.CL]. August 25, 2021.
  • Zuchao Li, Kevin Parnow, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama and Eiichiro Sumita. Cross-lingual Transferring of Pre-trained Contextualized Language Models. arXiv:2107.12627 [cs.CL]. July 27, 2021
  • Raj Dabre, Aizhan Imankulova, Masahiro Kaneko and Abhisek Chakrabarty. Simultaneous Multi-Pivot Neural Machine Translation. arXiv:2104.07410 [cs.CL]. April 15, 2021.
  • Raj Dabre, and Atsushi Fujita. Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation. arXiv:2106.10002 [cs.CL]. June 18, 2021.
  • Shohei Higashiyama, Masao Utiyama, Taro Watanabe and Eiichiro　Sumita. User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization. arXiv:2104.03523 [cs.CL]. April 8, 2021.
  • Zuchao Li, Zhuosheng Zhang, Hai Zhao, Rui Wang, Kehai Chen, Masao Utiyama and Eiichiro Sumita. Text Compression-aided Transformer Encoding. arXiv:2102.05951 [cs.CL]. February 11, 2021.
  • Rei Miyata and Atsushi Fujita. Understanding Pre-Editing for Black-Box Neural Machine Translation. arXiv:2102.02955 [cs.CL]. February 5, 2021.
  • Marie Benjamin and Atsushi Fujita. Synthesizing Monolingual Data for Neural Machine Translation. arXiv:2101.12462 [cs.CL]. January 29, 2021.

【解説 ほか】

  • 宮田　玲，藤田　篤. ニューラル機械翻訳を対象とした試行錯誤的プリエディット事例の探索的分析. AAMT Journal No.74, pages 15-22, June, 2021.