Peer-reviewed

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision

Ryo Yoshida, Taiga Someya, Yohei Oseki

Dissociating Syntactic Operations via Composition Count

Kohei Kajikawa, Ryo Yoshida, Yohei Oseki

Targeted Syntactic Evaluations on the Chomsky Hierarchy

Taiga Someya, Ryo Yoshida, Yohei Oseki

Localizing Syntactic Composition with Left-Corner Recurrent Neural Network Grammars

Yushi Sugimoto, Ryo Yoshida, Hyeonjeong Jeong, Masatoshi Koizumi, Jonathan R. Brennan, Yohei Oseki

Composition, Attention, or Both?

In this paper, we propose a novel architecture called Composition Attention Grammars (CAGs) that recursively compose subtrees into a …

Ryo Yoshida, Yohei Oseki

Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars

In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the …

Ryo Yoshida, Hiroshi Noji, Yohei Oseki

Lower Perplexity is Not Always Human-Like

In computational psycholinguistics, various language models have been evaluated against human reading behavior (e.g., eye movement) to …

Tatsuki Kuribayashi, Yohei Oseki, Takumi Ito, Ryo Yoshida, Masayuki Asahara, Kentaro Inui