Profile

Makoto Morishita

Ph.D.
NTT Communication Science Laboratories
Innovative Communication Laboratory
Linguistic Intelligence Research Group
morishita.makoto
makoto.anko
Twitter

Research Interests

• Machine Translation
• Natural Language Processing

Academic/Employment History

• 2012/04-2015/03 Doshisha University, Faculty of Science and Engineering
• (2013/02-2013/03 University of California, Irvine, Extension)
• 2015/04-2017/03 Nara Institute Science and Technology (NAIST), Graduate School of Information Sciences, Master's course, Augmented Human Communication Laboratory
• 2020/04-2022/03 Tohoku University, Graduate School of Information Sciences, Doctoral course, Fundamental Artificial Intelligence Laboratory
• 2017/04-onward NTT Communication Science Laboratories

Internship Experiences

• 2014/08-2014/09 SoftBank Mobile
• 2015/08-2015/09 NTT Communication Science Laboratories

Awards / Grants

• Feb. 2015, Doshisha University Excellent Student Award (Academic)
• May. 2016, Student Award, IPSJ SIG-NL and SIG-SLP
• Feb. 2017, Excellent Project Award, NAIST Creative and International Competitiveness Project (CICP), Chatomic
• Mar. 2017, The Best Student Award, Nara Institute Science and Technology
• Mar. 2017, NAIST The Best Student Award, Foundation for Nara Institute Science and Technology
• Apr. 2015 - Mar. 2017, JASSO Scholarship - Exemption from repayment with particularly outstanding academic achievements (Full exemption)
• Mar. 2019, Excellent Poster Award, NLP2019
• Mar. 2020, Young Encouragement Award, NLP2020
• Jun. 2021, AAMT Nagao Award, Asia-Pacific Association for Machine Translation (AAMT)
• Mar. 2022, Honorable mention, NLP2022
• Jun. 2022, AAMT Nagao Award Student Award, Asia-Pacific Association for Machine Translation (AAMT)

Certifications

• JITEC Applied Information Technology Engineer
• JITEC Information Security Specialist
• JITEC Network Specialist
• JITEC Database Specialist
• TOEIC 975

Activities

• 2012-2015, Doshisha Rohm Plaza Project
• 2015, NAIST Creative and International Competitiveness Project (CICP), Trapepper.
• 2016, NAIST Creative and International Competitiveness Project (CICP), Chatomic.
• Dec. 2016, COLING 2016 Student Volunteer
• 2020, 2021, 2022, IPSJ Kansai-branch Secretary
• 2020, 2021, 2022, Conference on Machine Translation (WMT), Organizer
• 2022, Workshop on Asian Translation (WAT), Task Organizer

Reviewer

• 2018, 2019, Workshop on Neural Generation and Translation (WNGT)
• 2020, 2021, 2022, 『自然言語処理』, 言語処理学会
• 2021, The ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)
• 2021, 2023, Annual Meeting of the Association for Computational Linguistics (ACL)
• 2021, 2022, Conference on Empirical Methods in Natural Language Processing (EMNLP)
• 2022, International Conference on Computational Linguistics (COLING)
• 2021, 2022, 2023, ACL Rolling Review (ARR)

Papers

Journal

• 帖佐 克己, 森下 睦, 永田 昌明.
  入力拡張と制約付きデコーディングによる語彙制約付き機械翻訳
  自然言語処理．29-4．2022年12月．
• 藤井 諒, 三田 雅人, 阿部 香央莉, 塙 一晃, 森下 睦, 鈴木 潤, 乾 健太郎.
  機械翻訳モデルの頑健性評価に向けた言語現象毎データセットの構築と分析
  自然言語処理．28-2．2021年6月．
• 森下 睦, 赤部 晃一, 波多腰 優斗, Graham Neubig, 吉野 幸一郎, 中村 哲.
  統語ベース翻訳のための構文解析器の自己学習
  自然言語処理．23-4．pp. 353-376, 2016年9月．

International Conference, Workshop

• Masaaki Nagata, Makoto Morishita, Katsuki Chousa, and Norihito Yasuda
  JaParaPat: A Large-Scale Japanese-English Parallel Patent Application Corpus
  The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. May 2024 (To Appear).
• Hayato Tsukagoshi, Tsutomu Hirao, Makoto Morishita, Katsuki Chousa, Ryohei Sasano and Koichi Takeda
  WikiSplit++: Easy Data Refinement for Split and Rephrase
  The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. May 2024 (To Appear).
• Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe
  Generating Diverse Translation with Perturbed kNN-MT
  The 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop. March 2024 (To Appear).
• Keito Kudo, Takumi Ito, Makoto Morishita, Jun Suzuki
  SKIM at WMT 2023 General Translation Task
  The 8th Conference on Machine Translation (WMT). December 2023.
• Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Philipp Koehn, Benjamin Marie, Christof Monz, Makoto Morishita, Kenton Murray, Makoto Nagata, Toshiaki Nakazawa, Martin Popel, Maja Popović, Mariya Shmatova, Jun Suzuki
  Findings of the 2023 Conference on Machine Translation (WMT23): LLMs Are Here but Not Quite There Yet
  The 8th Conference on Machine Translation (WMT). December 2023.
• Atsushi Shirafuji, Yusuke Oda, Jun Suzuki, Makoto Morishita, Yutaka Watanobe.
  Refactoring Programs Using Large Language Models with Few-Shot Examples
  The 30th Asia-Pacific Software Engineering Conference (APSEC 2023). December 2023.
• Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Kentaro Inui.
  An Investigation of Warning Erroneous Chat Translations in Cross-lingual Communication
  The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Student Research Workshop. November 2023.
• Toshiaki Nakazawa, Kazutaka Kinugawa, Hideya Mino, Isao Goto, Raj Dabre, Shohei Higashiyama, Shantipriya Parida, Makoto Morishita, Ondřej Bojar, Akiko Eriguchi, Yusuke Oda, Chenhui Chu, Sadao Kurohashi.
  Overview of the 10th Workshop on Asian Translation
  The 10th Workshop on Asian Translation (WAT). September 2023.
• Makoto Morishita, Jun Suzuki, Masaaki Nagata.
  Domain Adaptation of Machine Translation with Crowdworkers (Slides, Poster)
  The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) Industry Track. December 2022.
• Makoto Morishita*, Keito Kudo*, Yui Oka*, Katsuki Chousa*, Shun Kiyono, Sho Takase, Jun Suzuki (* Equal contribution).
  NT5 at WMT 2022 General Translation Task
  The 7th Conference on Machine Translation (WMT). December 2022.
• Tom Kocmi, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Thamme Gowda, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Rebecca Knowles, Philipp Koehn, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Michal Novák, Martin Popel, Maja Popović and Mariya Shmatova
  Findings of the 2022 Conference on Machine Translation (WMT22)
  The 7th Conference on Machine Translation (WMT). December 2022.
• Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Ryoko Tokuhisa, Ana Brassard, Kentaro Inui.
  Chat Translation Error Detection for Assisting Cross-lingual Communications
  The 3rd Workshop on Evaluation and Comparison of NLP Systems. November 2022.
• Toshiaki Nakazawa, Hideya Mino, Isao Goto, Raj Dabre, Shohei Higashiyama, Shantipriya Parida, Anoop Kunchukuttan, Makoto Morishita, Ondřej Bojar, Chenhui Chu, Akiko Eriguchi, Kaori Abe, Yusuke Oda, Sadao Kurohashi.
  Overview of the 9th Workshop on Asian Translation
  The 9th Workshop on Asian Translation (WAT). October 2022.
• Atsushi Shirafuji, Takumi Ito, Makoto Morishita, Yuki Nakamura, Yusuke Oda, Jun Suzuki, Yutaka Watanobe.
  Prompt Sensitivity of Language Model for Solving Programming Problems
  The 21st International Conference on Intelligent Software Methodologies, Tools, and Techniques (SOMET). September 2022.
• Makoto Morishita, Katsuki Chousa, Jun Suzuki, Masaaki Nagata.
  JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus (Poster, Slides)
  The 13th International Conference on Language Resources and Evaluation (LREC). June 2022.
• Farhad Akhbardeh, Arkady Arkhangorodsky, Magdalena Biesialska, Ondřej Bojar, Rajen Chatterjee, Vishrav Chaudhary, Marta R. Costa-jussa, Cristina España-Bonet, Angela Fan, Christian Federmann, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Leonie Harter, Kenneth Heafield, Christopher Homan, Matthias Huck, Kwabena Amponsah-Kaakyire, Jungo Kasai, Daniel Khashabi, Kevin Knight, Tom Kocmi, Philipp Koehn, Nicholas Lourie, Christof Monz, Makoto Morishita, Masaaki Nagata, Ajay Nagesh, Toshiaki Nakazawa, Matteo Negri, Santanu Pal, Allahsera Auguste Tapo, Marco Turchi, Valentin Vydrin, Marcos Zampieri.
  Findings of the 2021 Conference on Machine Translation (WMT21)
  The 6th Conference on Machine Translation (WMT). November 2021.
  
• Katsuki Chousa*, Makoto Morishita* (* Equal contribution).
  Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021
  The 8th Workshop on Asian Translation (WAT). August 2021.
• Makoto Morishita, Jun Suzuki, Tomoharu Iwata, Masaaki Nagata.
  Context-aware Neural Machine Translation with Mini-batch Embedding (Slides, Poster, Software)
  The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL). April 2021.
• Ryo Fujii, Masato Mita, Kaori Abe, Kazuaki Hanawa, Makoto Morishita, Jun Suzuki, Kentaro Inui.
  PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents (Poster, Data)
  The 28th International Conference on Computational Linguistics (COLING). December 2020.
• Loïc Barrault, Magdalena Biesialska, Ondřej Bojar, Marta R. Costa-jussà, Christian Federmann, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Matthias Huck, Eric Joanis, Tom Kocmi, Philipp Koehn, Chi-kiu Lo, Nikola Ljubešić, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Santanu Pal, Matt Post, Marcos Zampieri.
  Findings of the 2020 Conference on Machine Translation (WMT20)
  The 5th Conference on Machine Translation (WMT). November 2020.
  
• Shun Kiyono, Takumi Ito, Ryuto Konno, Makoto Morishita, Jun Suzuki.
  Tohoku-AIP-NTT at WMT 2020 News Translation Task (Poster)
  The 5th Conference on Machine Translation (WMT). November 2020.
  
• Makoto Morishita, Jun Suzuki, Masaaki Nagata.
  JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus
  The 12th International Conference on Language Resources and Evaluation (LREC). May 2020.
• Masaaki Nagata, Makoto Morishita.
  A Test Set for Discourse Translation from Japanese to English (Data)
  The 12th International Conference on Language Resources and Evaluation (LREC). May 2020.
• Hiroki Ikeuchi, Akio Watanabe, Tsutomu Hirao, Makoto Morishita, Masaaki Nishino, Yoichi Matsuo, Keishiro Watanabe.
  Recovery command generation towards automatic recovery in ICT systems by Seq2Seq learning
  IEEE/IFIP Network Operations and Management Symposium (NOMS) Mini-Conference. April 2020.
• Makoto Morishita*, Jun Suzuki*, Masaaki Nagata (* Equal contribution.).
  NTT's Neural Machine Translation Systems at WAT 2019 (Poster)
  The 6th Workshop on Asian Translation (WAT). November 2019.
• Soichiro Murakami*, Makoto Morishita*, Tsutomu Hirao, Masaaki Nagata (* Equal contribution.).
  NTT's Machine Translation Systems for WMT19 Robustness Task (Poster)
  The 4th Conference on Machine Translation (WMT). August 2019.
  First Place in the English-Japanese Track.
• Makoto Morishita, Jun Suzuki, Masaaki Nagata.
  NTT's Neural Machine Translation Systems for WMT 2018 (Poster)
  The 3rd Conference on Machine Translation (WMT). October 2018.
• Makoto Morishita, Jun Suzuki, Masaaki Nagata.
  Improving Neural Machine Translation by Incorporating Hierarchical Subword Features (Slides)
  The 27th International Conference on Computational Linguistics (COLING). August 2018.
• Jun Suzuki, Sho Takase, Hidetaka Kamigaito, Makoto Morishita, Masaaki Nagata.
  An Empirical Study of Building a Strong Baseline for Constituency Parsing (Supplementary Material)
  The 56th Annual Meeting of the Association for Computational Linguistics (ACL). July 2018.
• Makoto Morishita, Jun Suzuki, Masaaki Nagata.
  NTT Neural Machine Translation Systems at WAT 2017 (Poster, Slides, Scripts)
  The 4th Workshop on Asian Translation (WAT). November 2017.
  First place in all of the participated subtasks (ASPEC Ja-En, En-Ja, JIJI Ja-En, En-Ja).
• Makoto Morishita, Yusuke Oda, Graham Neubig, Koichiro Yoshino, Katsuhito Sudoh, Satoshi Nakamura.
  An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation (Poster)
  The 1st Workshop on Neural Machine Translation (WNMT). pp. 61-68. August 2017.
• Makoto Morishita, Koichi Akabe, Yuto Hatakoshi, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura.
  Parser Self-Training for Syntax-Based Machine Translation (Slides)
  The 12th International Workshop on Spoken Language Translation (IWSLT). pp. 232-239. December 2015.
• Graham Neubig, Makoto Morishita, Satoshi Nakamura.
  Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015 (Slides, Poster)
  The 2nd Workshop on Asian Translation (WAT). pp. 35-41. October 2015.

Technical Report

• Atsushi Shirafuji, Yutaka Watanobe, Takumi Ito, Makoto Morishita, Yuki Nakamura, Yusuke Oda, Jun Suzuki.
  Exploring the Robustness of Large Language Models for Solving Programming Problems
  arXiv preprint arXiv:2306.14583. June 2023.

Domestic Conference

• 西田 悠人, 森下 睦, 出口 祥之, 上垣外 英剛, 渡辺 太郎.
  kNN言語モデルは低頻度語の予測に役立つか？
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• 永田 昌明, 森下 睦, 帖佐 克己, 安田 宜仁.
  JaParaPat: 大規模日英特許対訳コーパス
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• 大鹿 雅史, 森下 睦, 平尾 努, 笹野 遼平, 武田 浩一.
  単語難易度を考慮した反復的な翻訳文の平易化
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• 森下 睦, 帖佐 克己, 永田 昌明.
  JParaCrawl v4.0: クラウドソーシングを併用した大規模対訳コーパスの構築
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• Yunmeng Li, 鈴木 潤, 森下 睦, 阿部 香央莉, 乾 健太郎.
  異言語間対話支援における誤訳警告メッセージの有効性調査
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• 近藤 海夏斗, 宇津呂 武仁, 森下 睦, 永田 昌明.
  対訳データを用いた継続事前訓練による大規模言語モデルの翻訳精度評価
  言語処理学会第28回年次大会(NLP2024). 兵庫. 2024年3月.
• 森下 睦.
  日英機械翻訳を世界に浸透させるために行った3つのこと
  NLP若手の会 第18回シンポジウム(YANS2023). 招待講演. 東京. 2023年8月.
• 西田 悠人, 森下 睦, 上垣外 英剛, 渡辺 太郎.
  単言語データを用いたLLMベースのkNN機械翻訳
  NLP若手の会 第18回シンポジウム(YANS2023). 東京. 2023年8月.
• 西田 悠人, 森下 睦, 上垣外 英剛, 渡辺 太郎.
  摂動を加えたkNN機械翻訳による多様な翻訳候補の生成
  言語処理学会第28回年次大会(NLP2023). 沖縄. 2023年3月.
• 駒田 啓伍, 森下 睦, 鈴木 潤.
  文単位のNbest候補制約に基づく文書翻訳
  言語処理学会第28回年次大会(NLP2023). 沖縄. 2023年3月.
  高電社賞.
• 伊藤 拓海, 森下 睦, 鈴木 潤.
  自然言語生成タスクの自動評価指標のためのドメイン外検出
  言語処理学会第28回年次大会(NLP2023). 沖縄. 2023年3月.
• Yunmeng Li, 鈴木 潤, 森下 睦, 阿部 香央莉, 徳久 良子, Ana Brassard, 乾 健太郎.
  異言語間対話を支援する日英雑談対話誤訳検出
  言語処理学会第28回年次大会(NLP2023). 沖縄. 2023年3月.
• 森下 睦, 帖佐克己, 鈴木 潤, 永田 昌明.
  JParaCrawl v3.0: 大規模日英対訳コーパス (Poster)
  言語処理学会第28回年次大会(NLP2022). オンライン. 2022年3月.
  委員特別賞.
• 塚越 駿, 平尾 努, 森下 睦, 帖佐 克己, 笹野 遼平, 武田 浩一.
  自然言語推論と再現器を用いたSplit and Rephraseにおける生成文の品質向上
  言語処理学会第28回年次大会(NLP2022). オンライン. 2022年3月.
• Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Ryoko Tokuhisa, Ana Brassard, Kentaro Inui.
  BPersona-chat: A Coherence-Filtered Japanese-English Dialogue Corpus
  言語処理学会第28回年次大会(NLP2022). オンライン. 2022年3月.
• 李 云蒙, 阿部 香央莉, 徳久 良子, 森下 睦, 鈴木 潤, 乾 健太郎.
  Towards Detecting Errors of Chat Translation: Evaluating Translated Chat with Classifiers and Building Auto-Evaluatable Translation Chat System
  NLP若手の会 第16回シンポジウム(YANS). オンライン. 2021年8月.
• 森下 睦, 鈴木 潤, 永田 昌明.
  クラウドソーシングによるWebサイトマイニングを用いた翻訳モデルの即時領域適応 (Poster)
  言語処理学会第27回年次大会(NLP2021). オンライン. 2021年3月.
• Yunmeng Li, Ryo Fujii, Makoto Morishita, Jun Suzuki, Kentaro Inui.
  Towards Detecting Errors: Classifying Model-Generated Output in Chat Translation
  言語処理学会第27回年次大会(NLP2021). オンライン. 2021年3月.
• 藤井 諒, 三田 雅人, 阿部 香央莉, 塙 一晃, 森下 睦, 鈴木 潤, 乾 健太郎.
  ユーザ生成コンテンツの高品質な自動翻訳に向けた言語現象の体系的分析
  2020年度 人工知能学会全国大会(JSAI2020). 熊本. 2020年6月.
• 森下 睦, 鈴木 潤, 永田 昌明.
  JParaCrawl: 大規模Webベース日英対訳コーパス (Slides)
  言語処理学会第26回年次大会(NLP2020). 茨城. 2020年3月. 若手奨励賞.
• 永田 昌明, 森下 睦.
  日本語から英語への文脈翻訳テストの提案
  言語処理学会第25回年次大会(NLP2019). 愛知. 2019年3月.
• 村上 聡一朗, 松岡 保静, 内田 渉, 礒田 佳徳, 森下 睦, 平尾 努, 永田 昌明.
  自然発話に頑健な機械翻訳の検討
  言語処理学会第25回年次大会(NLP2019). 愛知. 2019年3月.
• 森下 睦, 鈴木 潤, 永田 昌明.
  双方向学習と再現学習を統合したニューラル機械翻訳 (Poster)
  言語処理学会第25回年次大会(NLP2019). 愛知. 2019年3月. 優秀ポスター賞.
• 森下 睦, 鈴木 潤, 永田 昌明.
  階層的な部分単語を入力としたニューラル機械翻訳 (Poster)
  2018年度 人工知能学会全国大会(JSAI2018). 鹿児島. 2018年6月.
• 森下 睦, 小田 悠介, Graham Neubig, 吉野 幸一郎, 須藤 克仁, 中村 哲.
  ニューラル機械翻訳におけるミニバッチ構成法の違いによる影響の調査 (Slides)
  言語処理学会第23回年次大会(NLP2017). 茨城. 2017年3月.
• 森下 睦, Graham Neubig, 吉野 幸一郎, 中村 哲.
  構文木の生成確率を考慮した対訳コーパスを用いた構文解析器の自己学習 (Poster)
  NLP若手の会 第11回シンポジウム(YANS). 和歌山. 2016年8月.
• 森下 睦, 小田 悠介, Graham Neubig, 吉野 幸一郎, 中村 哲.
  様々な分野における対訳コーパスを用いた構文解析器の自己学習効果の検証 (Slides, Data)
  情報処理学会 第223回自然言語処理研究会(SIG-NL). 東京. 2016年5月. 学生奨励賞.
• 森下 睦, 赤部 晃一, 波多腰 優斗, Graham Neubig, 吉野 幸一郎, 中村 哲.
  対訳コーパスを利用した構文解析器の自己学習 (Slides)
  言語処理学会第22回年次大会(NLP2016). 仙台. 2016年3月.
• 森下 睦, 赤部 晃一, Graham Neubig, 吉野 幸一郎, 中村 哲.
  機械翻訳の精度を考慮した構文解析器の自己学習 (Slides)
  情報処理学会 第223回自然言語処理研究会(SIG-NL). 広島. 2015年9月.

Software and Resources

• JParaCrawl
  A large English-Japanese parallel corpus based on the web.
  
• Scripts for reproducing WAT 2017 NMT system
  Scripts for reproducing the neural machine translation system that achieved the best in WAT 2017.
  
• Open-domain Japanese syntax parsing model
  Self-trained open-domain Japanese syntax parsing model for Berkeley Parser and Egret.
  
• Sentence similarity checker using encoder-decoder model
  Tool for calculating sentence similarity based on the encoder-decoder model.