10 citations · 36 across the 26 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CL2022
Composition, Attention, or Both?
Ryo Yoshida, Yohei Oseki
In this paper, we propose a novel architecture called Composition Attention Grammars (CAGs) that recursively compose subtrees into a single vector representation with a composition…
cs.CL2022★ 8 cited
Context Limitations Make Neural Language Models More Human-Like
Tatsuki Kuribayashi, Yohei Oseki, Ana Brassard +1
Language models (LMs) have been used in cognitive modeling as well as engineering studies -- they compute information-theoretic complexity metrics that simulate humans' cognitive l…