Construction and evaluation of neurocomputational models of natural language
- 1.4 Cognitive science
- 1.5 Neuroscience
- 3.8 Informatics
Yohei Oseki
Graduate School of Arts and Sciences
Lecturer
※ Finished end of FY2021
In this research project, we will investigate computational and neural bases of language by constructing neurocomputational models based on symbolic automata and neural networks and evaluating them with neurophysiological measurements of human magnetoencephalography and electrocorticography.
In this research project, we will investigate computational and neural bases of language by constructing neurocomputational models based on symbolic automata and neural networks and evaluating them with neurophysiological measurements of human magnetoencephalography and electrocorticography.
Credit：Innovative Area Research: Correspondence and Fusion of Artificial Intelligence and Brain Science
Related links
Research collaborators
- Waseda University
- Sumitomo Heavy Industries, Ltd.
- TMG Asaka Medical Center
- National Rehabilitation Center for Persons with Disabilities
Related publications
- Tatsuki Kuribayashi, Yohei Oseki, et al. Lower Perplexity is Not Always Human-Like. ACL, 5203-5217, 2021.
- Hiroshi Noji, Yohei Oseki. Effective Batching for Recurrent Neural Network Grammars. ACL, 4340-4352, 2021.
Contact
- Graduate School of Arts and Sciences
- Tel: +81-3-5454-6388
- Email: oseki[at]g.ecc.u-tokyo.ac.jp
※[at]=@
