平澤 寅庄 (Tosho Hirasawa)

Updated: Nov 26, 2023

Profile

Interests

  1. Natural Language Processing（自然言語処理）
  2. Vision & Language (視覚と言語)
  3. Machine Translation（機械翻訳）

Publications

論文誌

  1. Hwichan Kim, Hirasawa Tosho, Sangwhan Moon, Naoaki Okazaki and Mamoru Komachi.North Korean Neural Machine Translation through South Korean Resources. ACM Transactions on Asian and Low-Resource Language Information Processing. Volume 22, Issue 9. 2023. [paper]
  2. Tosho Hirasawa, Masahiro Kaneko, Aizhan Imankulova, Mamoru Komachi. Pre-Trained Word Embedding and Language Model Improve Multimodal Machine Translation: A Case Study in Multi30K. IEEE Access. Volume: 10. 2022. [paper]
  3. Zhishen Yang, Tosho Hirasawa, Naoaki Okazaki, Mamoru Komachi. Why Videos do not Guide Translations in Video-guided Machine Translation? An Empirical Evaluation of Video-guided Machine Translation Dataset. 情報処理学会論文誌 データベース(TOD). 15巻 2号. 2022. [paper]
  4. 喜友名 朝視顕, 平澤 寅庄, 小町 守, 小木曽 智信. 事前学習モデルを用いた近代文語文のニューラル機械翻訳. 情報処理学会論文誌. 63巻2号. 2021. [web]

国際会議

2023

  1. Tosho Hirasawa, Emanuele Bugliarello (University of Copenhagen), Desmond Elliott (University of Copenhagen) and Mamoru Komachi (Hitotsubashi University). Visual Prediction Improves Zero-Shot Cross-Modal Machine Translation. The Eight Conference on Machine Translation (WMT 2023). Singapore. December, 2023.
  2. Taisei Enomoto, Tosho Hirasawa, Hwichan Kim, Teruaki Oka (Hitotsubashi University) and Mamoru Komachi (Hitotsubashi University). Simultaneous Domain Adaptation of Tokenization and Machine Translation. The 37th Pacific Asia Conference on Language, Information and Computation (PACLIC 37). Hong Kong. December, 2023.
  3. Hiroto Tamura, Tosho Hirasawa, Hwichan Kim and Mamoru Komachi. Does Masked Language Model Pre-training with Artificial Data Improve Low-resource Neural Machine Translation? Findings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023). Dubrovnik. May, 2023.

2022

  1. Daisuke Suzuki, Yujin Takahashi, Ikumi Yamashita, Taichi Aida, Tosho Hirasawa, Michitaka Nakatsuji, Masato Mita and Mamoru Komachi. Construction of a Quality Estimation Dataset for Automatic Evaluation of Japanese Grammatical Error Correction. The 13th Edition of Language Resources and Evaluation Conference (LREC 2022). Marseille. May, 2022. [paper]

2021

  1. Seiichiro Kondo, Aomi Koyama, Tomoshige Kiyuna, Tosho Hirasawa and Mamoru Komachi. Machine Translation with Pre-specified Target-side Words Using a Semi-autoregressive Model. The 8th Workshop on Asian Translation, pp.68-73. Online. August, 2021. [paper]
  2. Seiichiro Kondo, Kengo Hotate, Tosho Hirasawa, Masahiro Kaneko and Mamoru Komachi. Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation. NAACL Student Research Workshop (SRW) 2021. Online. June, 2021. (accepted) [paper]
  3. Zhishen Yang (Tokyo Institute of Technology), Tosho Hirasawa, Naoaki Okazaki (Tokyo Institute of Technology), Mamoru Komachi. Do Videos Guide Translations? Evaluation of a Video-Guided Machine Translation dataset. In Proceedings of the Workshop on Visually Grounded Interaction and Language. Online. June 10, 2021. [paper]

2020

  1. Zizheng Zhang, Tosho Hirasawa, Wei Houjing, Masahiro Kaneko and Mamoru Komachi. Translation of New Named Entities from English to Chinese. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp.58-63. Suzhou. December, 2020.
  2. Hiroto Tamura, Tosho Hirasawa, Masahiro Kaneko and Mamoru Komachi. TMU Japanese-English Multimodal Machine Translation System for WAT 2020. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp. 80-91. Suzhou. December, 2020.
  3. Hwichan Kim, Tosho Hirasawa and Mamoru Komachi. Korean to Japanese Neural Machine Translation System Using Hanja Information. In Proceedings of the 7th Workshop on Asian Translation (WAT), pp. 127-134. Suzhou. December, 2020.
  4. Aizhan Imankulova, Masahiro Kaneko, Tosho Hirasawa and Mamoru Komachi. Towards Multimodal Simultaneous Neural Machine Translation. In 2020 Fifth Conference on Machine Translation (WMT). Online. November, 2020.
  5. Masashi Takaku, Tosho Hirasawa, Mamoru Komachi, Kanako Komiya. Neural Machine Translation from Historical Japanese to Contemporary Japanese Using Diachronically Domain-Adapted Word Embeddings. The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC 34). Hanoi. October, 2020. [Paper]
  6. Hwichan Kim, Tosho Hirasawa and Mamoru Komachi. Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL 2020 SRW), pp.72-78. Online. July, 2020.
  7. Masahiro Kaneko, Aizhan Imankulova, Tosho Hirasawa and Mamoru Komachi. English-to-Japanese Diverse Translation by Combining Forward and Backward Outputs. In Proceedings of The 4th Workshop on Neural Generation and Translation (WNGT 2020), Online. pp.134-138. July, 2020.
  8. Tosho Hirasawa, Zhishen Yang, Mamoru Komachi and Naoaki Okazaki. Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020. In Workshop on Advances in Language and Vision Research. Online. July, 2020.

2019

  1. Tosho Hirasawa and Mamoru Komachi. Debiasing Word Embeddings Improves Multimodal Machine Translation. In Proceedings of the 17th Machine Translation Summit (MT Summit 2019). Dublin. August, 2019. [web [arXiv] [poster] [boaster]
  2. Tosho Hirasawa, Hayahide Yamagishi, Yukio Matsumura, Mamoru Komachi. Multimodal Machine Translation with Embedding Prediction. In NAACL Student Research Workshop (SRW) 2019. Minneapolis. June, 2019. [web] [arXiv] [code] [slide]

国内会議

  1. 平澤寅庄, 小町守. 視覚翻訳言語モデルを用いた英日マルチモーダル機械翻訳. 言語処理学会第28回年次大会. 宜野湾. 2023年3月. [論文] [コード]
  2. 佐藤郁子, 平澤寅庄, 金輝燦, 岡照晃, 小町守. マルチモーダル機械翻訳における画像・入力文間類似度と翻訳品質の相関の分析. 言語処理学会第28回年次大会. 宜野湾. 2023年3月. [論文]
  3. 榎本大晟, 平澤寅庄, 金輝燦, 岡照晃, 小町守. ニューラル機械翻訳における単語分割器のドメイン適応. 言語処理学会第28回年次大会. 宜野湾. 2023年3月. [論文]
  4. 木山朔, 金輝燦, 平澤寅庄, 岡照晃, 小町守. Decoder のみを用いた機械翻訳モデルの分析. 言語処理学会第28回年次大会. 宜野湾. 2023年3月. [論文]
  5. 田村弘人, 平澤寅庄, 金輝燦, 岡照晃, 小町守. 人工データでの事前学習によるニューラル機械翻訳の性能向上. 言語処理学会第28回年次大会. オンライン. 2022年3月. [論文]
  6. 蘆田 真奈, 平澤寅庄, 金子 正弘, 小町 守. 日本語 BERT による否定表現認識についての分析. 言語処理学会第27回年次大会. オンライン. 2021年3月. [論文]
  7. 喜友名 朝視顕, 平澤寅庄, 小町 守, 小木曽 智信（国語研）. 事前学習モデルを用いた近代文語文の現代語機械翻訳. 言語処理学会第27回年次大会. オンライン. 2021年3月. [論文]
  8. 今藤 誠一郎, 甫立 健悟, 平澤寅庄, 金子 正弘, 小町 守. 2 文の連結を用いた機械翻訳におけるデータ拡張. 言語処理学会第27回年次大会. オンライン. 2021年3月. [論文]
  9. 金輝燦（朝鮮大）, 平澤寅庄, 小町守. 韓国語対訳データを利用した文字分割と音素分解による朝鮮語ニューラル機械翻訳. 言語処理学会第26回年次大会. オンライン. 2020年3月. [論文]
  10. 高久雅史（茨城大）, 平澤寅庄, 小町守, 古宮嘉那子（茨城大）. 通時的な領域適応を行った単語分散表現を利用した古文から現代文へのニューラル機械翻訳. 言語処理学会第26回年次大会. オンライン. 2020年3月. [論文]
  11. 平澤寅庄, 山岸駿秀, 松村雪桜, 小町守. 事前学習した単語分散表現を利用したマルチモーダル機械翻訳. 言語処理学会第25回年次大会. 名古屋. 2019年3月. [論文] [ポスター]