SAC Highlight Award at ACL 2026
Our paper on human-like inductive biases for improving LLM data efficiency received an SAC Highlight Award at ACL 2026.
Taiga Someya
Taiga Someya is a Ph.D. student at the University of Tokyo, focusing on natural language processing and deep learning for sports analytics. Former soccer U-15/16 Japan national team candidate and Kashiwa Reysol U-18 player.
Latest news
View all news →Two papers accepted to ACL 2026
Two papers were accepted to the ACL 2026 Main Conference, on language acquisition in language models and garden-path effects via surprisal.
Invited talks at UCI and Boston University
I will give invited talks at UCI and Boston University.
Selected publications
View all publications →Language Acquisition Device in Large Language Models
Masato Mita, Taiga Someya, Ryo Yoshida, Yohei OsekiACL 2026
★ SAC Highlight Award
Derivational Probing: Unveiling the Layer-wise Construction of Syntactic Structures in Neural Language Models
Taiga Someya, Ryo Yoshida, Hitomi Yanaka, Yohei OsekiCoNLL 2025
★ Oral
Information Locality as an Inductive Bias for Neural Language Models
Taiga Someya, Anej Svete, Brian DuSell, Timothy J. O'Donnell, Mario Giulianelli, Ryan CotterellACL 2025
★ Oral + Panel (Top 0.8%)
Targeted Syntactic Evaluations on the Chomsky Hierarchy
Taiga Someya, Ryo Yoshida, Yohei OsekiLREC-COLING 2024
★ Best Paper Award (1/1554; Top 0.06%)
