安永迪弘 / Michihiro Yasunaga (Stanford University)
[Webサイト]Michihiro Yasunaga is a PhD student in Computer Science at Stanford University, advised by Prof. Percy Liang and Prof. Jure Leskovec. His research lies in natural language processing and machine learning. His recent research focuses on language models, knowledge representations, and multimodal learning. His research was recognized by the Microsoft Research PhD Fellowship 2022. Prior to Stanford, he obtained a B.S. in Computer Science from Yale University.
概要
Teaching machines to reason over texts has been a long-standing goal of natural language processing (NLP). In this tutorial, we will review (1) complex reasoning tasks that involve compositional reasoning, knowledge retrieval, grounding, commonsense reasoning, etc. and (2) knowledge-augmented training approaches to enhance the reasoning performance of NLP models.
※トークは日本語です。