Associate Professor, the University of Tokyo, Neuro-Symbolic AI for Language Understanding
#NLProc
東大 博士(工学)→理研→東大IS/CS 准教授|卓越研究員・谷中研究室|JSTさきがけ|人工知能学会理事 ダンモOB
NAACL 2024(main)に論文が採択されました!
"On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons"
NLP2024@神戸で昨日まさに発表した研究(のアップデート版)になります!
主著論文と共著論文2件が
#ACL2021NLP
Findingsに採択されました!Glad to see our two
#ACL2021NLP
papers "SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics" & "Do Grammatical Error Correction Models Realize Grammatical Generalization?" have been accepted!
To what extent are DNN models capable of learning the compositional generalization underlying NLI from given training instances? Check out our
#acl2020nlp
paper "Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?”
#NLProc
#ACL2023
で主著・共著計7件を発表します!皆さんとトロント(・オンライン)でお話できるのを楽しみにしています!Yanaka Lab from the Univ. of Tokyo will have 7 presentations at
#ACL2023NLP
! Looking forward to seeing
#NLProc
friends in Toronto soon! A thread (details):