Biography

I’m Ryo Yoshida, a Ph.D student at the Department of Language and Information Sciences, Graduate School of Arts and Sciences, University of Tokyo. I’m working with Yohei Oseki on natural language processing, cognitive modeling, and syntactic supervision.

Interests
  • Natural Language Processing
  • Cognitive Modeling
  • Syntactic Supervision
Education

  • Doctor of Arts, April 2023 - Present

    Department of Language and Information Sciences, Graduate School of Arts and Sciences, University of Tokyo

  • Master of Arts, April 2021 - March 2023

    Department of Language and Information Sciences, Graduate School of Arts and Sciences, University of Tokyo

  • Bachelor of Arts, April 2017 - March 2021

    Department of Humanities and Social Sciences, College of Arts and Sciences, University of Tokyo

Skills

Python

4 years

R

A little

haskell_logo_icon_170039
Haskell

Beginner

Experience

 
 
 
 
 
CTO
Jool Corp.
Apr 2022 – Mar 2024 Kyoto
 
 
 
 
 
学術専門職員
The University of Tokyo
Nov 2021 – Mar 2023 Tokyo
 
 
 
 
 
AI engineering internship
ELYZA, Inc.
May 2020 – Oct 2022 Tokyo

Grants

Japan Society for Promotion of Science (JSPS) Research Fellowship for Young Scientists (DC2)
200,000 yen / month + 1,500,000 yen
April 2024 - March 2026
Apr 1, 2024
日本学生支援機構奨学金 特に優れた業績による返還免除（全額免除）
1,200,000 yen
Jul 7, 2023
グリーントランスフォーメーション (GX) を先導する高度人材育成 (SPRING GX)
180,000 yen / month + 340,000 yen / year
April 2023 - March 2026
Apr 1, 2023

Recent Publications

Taiga Someya, Ryo Yoshida, Hitomi Yanaka, Yohei Oseki (2025). Derivational Probing: Unveiling the Layer-wise Derivation of Syntactic Structures in Neural Language Models. Proceedings of the 29th Conference on Computational Natural Language Learning (acceptance rate: 18.4%).

Cite DOI URL

Masato Mita, Ryo Yoshida, Yohei Oseki (2025). Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (acceptance rate: 20.3%).

Cite DOI URL

Ryo Yoshida, Shinnosuke Isono, Kohei Kajikawa, Taiga Someya, Yushi Sugimoto, Yohei Oseki (2025). If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (acceptance rate: 20.3%).

Cite DOI URL

Ryo Yoshida, Yushi Sugimoto, Yohei Oseki (2025). Investigating Psychometric Predictive Power of Syntactic Attention. Proceedings of the 29th Conference on Computational Natural Language Learning (acceptance rate: 18.4%).

Cite DOI URL

Tatsuki Kuribayashi, Ryo Ueda, Ryo Yoshida, Yohei Oseki, Ted Briscoe, Timothy Baldwin (2024). Emergent Word Order Universals from Cognitively-Motivated Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (acceptance rate: 21.3%).

Cite DOI URL

See all publications

Awards

Best Paper Award at NLP2024 (domestic conference)（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」
Mar 10, 2025
Best Paper Award at LREC-COLING2024 (international conference) (1/1554=0.06%)
“Targeted Syntactic Evaluations on the Chomsky Hierarchy”
May 24, 2024
Outstanding Paper Award at NLP2024 (domestic conference)（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—」
Mar 11, 2024
一高記念賞（東京大学大学院 総合文化研究科）
「Human-Like Language Models: Composition, Attention, or Both?」
Mar 23, 2022
Special Committee Award at NLP2021 (domestic conference)（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」
Mar 15, 2021
Young Researcher Award at NLP2021 (domestic conference)（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」
Mar 15, 2021

Contact