Ryo Yoshida / 吉田 遼

Publications

International

2026

• An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal
  Ryo Yoshida, Shinnosuke Isono, Taiga Someya, Yohei Oseki, Tatsuki Kuribayashi
  Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers) (ACL 2026) (acceptance rate: 18.9%)
• Language Acquisition Device in Large Language Models
  Masato Mita, Taiga Someya, Ryo Yoshida, Yohei Oseki
  Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers) (ACL 2026) (acceptance rate: 18.9%)
  ★ SAC Highlight
• Brain-to-Text Decoding with Brain Atlases and Brain Foundation Models
  Haruka Akama, Ryo Yoshida, Max Müller-Eberstein, Yohei Oseki
  Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2026)
• Rethinking the Relationship between the Power Law and Hierarchical Structures
  Kai Nakaishi, Ryo Yoshida, Kohei Kajikawa, Koji Hukushima, Yohei Oseki
  To appear in Transactions of the Association for Computational Linguistics (TACL)

2025

• Investigating Psychometric Predictive Power of Syntactic Attention
  Ryo Yoshida, Yushi Sugimoto, Yohei Oseki
  Proceedings of the 29th Conference on Computational Natural Language Learning (CoNLL 2025) (acceptance rate: 18.4%)
• Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models
  Taiga Someya, Ryo Yoshida, Hitomi Yanaka, Yohei Oseki
  Proceedings of the 29th Conference on Computational Natural Language Learning (CoNLL 2025) (acceptance rate: 18.4%)
• If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
  Ryo Yoshida, Shinnosuke Isono, Kohei Kajikawa, Taiga Someya, Yushi Sugimoto, Yohei Oseki
  Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2025) (acceptance rate: 20.3%)
• Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition
  Masato Mita, Ryo Yoshida, Yohei Oseki
  Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2025) (acceptance rate: 20.3%)

2024

• Emergent Word Order Universals from Cognitively-Motivated Language Models
  Tatsuki Kuribayashi, Ryo Ueda, Ryo Yoshida, Yohei Oseki, Ted Briscoe, Timothy Baldwin
  Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2024) (acceptance rate: 21.3%)
• Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision
  Ryo Yoshida, Taiga Someya, Yohei Oseki
  Findings of the Association for Computational Linguistics: ACL 2024 (ACL 2024 Findings) (acceptance rate: 43.4%)
• Dissociating Syntactic Operations via Composition Count
  Kohei Kajikawa, Ryo Yoshida, Yohei Oseki
  Annual Meeting of the Cognitive Science Society (CogSci 2024) (oral presentation acceptance rate: 19%)
• Targeted Syntactic Evaluations on the Chomsky Hierarchy
  Taiga Someya, Ryo Yoshida, Yohei Oseki
  Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING) (LREC-COLING 2024) (acceptance rate: 44%)
  ★ Best Paper Award
• Localizing Syntactic Composition with Left-Corner Recurrent Neural Network Grammars
  Yushi Sugimoto, Ryo Yoshida, Hyeonjeong Jeong, Masatoshi Koizumi, Jonathan R. Brennan, Yohei Oseki
  Neurobiology of Language, Vol. 5, No. 1, pp. 201–224 (2024)

2022

• Composition, Attention, or Both?
  Ryo Yoshida, Yohei Oseki
  Findings of the Association for Computational Linguistics: EMNLP 2022 (EMNLP 2022 Findings) (acceptance rate: 36%)
• Learning Argument Structures with Recurrent Neural Network Grammars
  Ryo Yoshida, Yohei Oseki
  Proceedings of the Society for Computation in Linguistics (SCiL 2022) (oral presentation acceptance rate: 47.4%)

2021

• Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
  Ryo Yoshida, Hiroshi Noji, Yohei Oseki
  Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) (acceptance rate: 17.9%)
• Lower Perplexity is Not Always Human-Like
  Tatsuki Kuribayashi, Yohei Oseki, Takumi Ito, Ryo Yoshida, Masayuki Asahara, Kentaro Inui
  Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (ACL-IJCNLP 2021) (acceptance rate: 21.3%)

Domestic

Grants

• JST ACT-X — Oct 2025 – Mar 2028 · 4,500,000 yen
• JSPS Research Fellowship for Young Scientists (DC2) — Apr 2024 – Mar 2026 · 200,000 yen / month + 1,500,000 yen
• SPRING GX — Apr 2023 – Mar 2026 · 180,000 yen / month + 340,000 yen / year

Awards

• SAC Highlight at ACL 2026
  "Language Acquisition Device in Large Language Models"
• Special Committee Award at NLP2026 (言語処理学会第32回年次大会, 委員特別賞, 32/748=4.3%)
  「言語モデルの言語獲得装置」
• Best Paper Award at NLP2025 (言語処理学会第31回年次大会, 最優秀賞, 1/765=0.1%)
  「作業記憶の発達的特性が言語獲得の臨界期を形成する」
• Best Paper Award at LREC-COLING 2024 (1/1554=0.06%)
  "Targeted Syntactic Evaluations on the Chomsky Hierarchy"
• Outstanding Paper Award at NLP2024 (言語処理学会第30回年次大会, 優秀賞, 12/599=2.0%)
  「どのような言語モデルが不可能な言語を学習してしまうのか？---語順普遍を例に---」
• Best Master's Thesis Award (東京大学大学院 総合文化研究科 一高記念賞, 2023)
  "Human-Like Language Models: Composition, Attention, or Both?"
• Young Researcher Award at NLP2021 (言語処理学会第27回年次大会, 若手奨励賞, 11/247=4.5%)
  「再帰的ニューラルネットワーク文法による人間の文処理のモデリング」
• Special Committee Award at NLP2021 (言語処理学会第27回年次大会, 委員特別賞, 14/361=3.8%)
  「予測の正確な言語モデルがヒトらしいとは限らない」

Experience

• CTO, Jool Corp. — Apr 2026 – Present
• Research Part-time Worker, Isono Laboratory, NINJAL — Apr 2026 – Present
• Research Part-time Worker, Yanaka Laboratory, RIKEN — Nov 2025 – Present
• JSPS Research Fellow (DC2), Japan Society for the Promotion of Science — Apr 2024 – Mar 2026
• CTO, Jool Corp. — Apr 2022 – Mar 2024
• Research Staff, The University of Tokyo — Nov 2021 – Mar 2023
• AI Engineering Internship, ELYZA, Inc. — May 2020 – Oct 2022

Education

• Doctor of Arts, Department of Language and Information Sciences, Graduate School of Arts and Sciences, The University of Tokyo — Apr 2023 – Mar 2027 (expected) (Supervisor: Prof. Yoshifumi Kawasaki)
• Master of Arts, Department of Language and Information Sciences, Graduate School of Arts and Sciences, The University of Tokyo — Apr 2021 – Mar 2023
• Bachelor of Arts, Department of Humanities and Social Sciences, College of Arts and Sciences, The University of Tokyo — Apr 2017 – Mar 2021