Prof. Dr.Eng. Mamoru Komachi, M.Eng.

Tokyo Metropolitan University, Japan

Presentation’s Download

Mamoru Komachi is a Professor at Tokyo Metropolitan University (TMU). He received his M.Eng. and Ph.D. degrees from Nara Institute of Science and Technology (NAIST) in 2007 and 2010. He was an Assistant Professor at NAIST before joining TMU. His research interests include semantics, information extraction and educational applications of natural language processing.

Recent Advances in Natural Language Understanding and Natural Language Generation

In the last decade, the deep learning-based approach has become widely used in the field of naturallanguage processing. Especially after 2018, two major trends were born. One is a breakthrough in the method of learning a huge neural network by self-supervised learning using a large-scale text corpus. Pre-training of neural networks has been shown to be effective in a variety of languageunderstanding tasks and has greatly advanced the limit of naturallanguage processing. The other is fluent languagegeneration by neural networks, and it has become clear that neural methods can produce outputs that are seemingly indistinguishable from human outputs in various generation tasks such as machine translation and have received great attention. In this talk, I would like to give an overview of the trends in these technologies in naturallanguage processing, address ethical and social issues, and deepen discussions on future developments.