🧑‍🔬 Yohei Oseki

🏛️ Affiliations

🎓The University of TokyoTokyo · Japan2021–2026 · 77 paperscurrent🔬National Institute for Japanese Language and LinguisticsTokyo · Japan2026 · 3 paperscurrent🔬National Institute of InformaticsTokyo · Japan2026 · 1 papercurrent🎓Waseda UniversityTokyo · Japan2019–2021 · 6 papers🔬RIKENWako · Japan2021–2025 · 5 papers🎓New York UniversityNew York · United States2018–2020 · 3 papers🔬Artificial Intelligence Research CenterTokyo · Japan2021–2023 · 2 papers🔬National Institute of Advanced Industrial Science and TechnologyTsukuba · Japan2021–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Topics

🧒 Psycholinguistics & language acquisition (3)🧠 Language models & pretraining (1)📏 Evaluation & benchmarks (1)

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Targeted Syntactic Evaluation on the Chomsky Hierarchy (2024 · 10 citations)
   The authors propose a new approach to Targeted Syntactic Evaluation. Rather than testing individual grammatical phenomena, they examine how language models handle constructions of varying complexity according to the Chomsky hierarchy. To this end, four artificial formal languages are constructed, each modeling a…
2. Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition (2025 · 9 citations)
   LLMs need far more training data than children to reach comparable linguistic competence. Drawing on the Critical Period Hypothesis and Newport's Less-is-More Hypothesis, the authors test whether mimicking how children's working memory grows can make LM training more data-efficient. They model working-memory growth…
3. BabyLM Challenge: Curriculum learning based on sentence complexity approximating language acquisition (2023 · 9 citations)
   The BabyLM Challenge is a shared task in which language models are trained on a small corpus. Its size approximates the amount of language a child hears at an early age. The authors built on the fact that adults first speak to young children in simple, short phrases, and the complexity of speech increases as the…
4. An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal (2026 · 1 citation)
   Neural language models (LMs) estimate reading difficulty well on simple, naturalistic text. On garden-path sentences, however, their surprisal predicts far less slowdown than humans actually show. Several researchers have taken this gap as evidence that syntactic disambiguation cost lies outside surprisal theory.…
5. Rethinking the Relationship between the Power Law and Hierarchical Structures (2026)
   Across many corpora, the statistical dependence between linguistic units (phones, characters, words) weakens with distance following a power law rather than an exponential curve.

Also in our library

2 more works of theirs are in our library without a page here yet; they will appear as we publish them.

🤝 Co-authors here

4 co-authors with a page, the most papers together first.

• Ryo Yoshida ×4
• Taiga Someya ×2
• Masato Mita
• Tatsuki Kuribayashi

🔗 Cited by

Papers of our library cite their works 36 times (of the 140,884 papers whose bibliographies we read); 2 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yohei-oseki/