날짜 : 2022년 8월 24일 수요일, 오후 16시
장소 : 제 1공학관 A528

제목: Human-centric NLP: Learning from human perceptions, interactions, and disagreements

abstract:NLP systems trained in classifical ML pipeline suffer from the lack of robustness, interpretability, and controllability. This talk will propose a human-centric NLP pipeline that allows the model to learn more from human perceptions, interactions with humans, disagreements among diverse humans.

bio:DongYeop Kang (DK) is an assistant professor in the Computer Science Engineering department at the University of Minnesota, Twin Cities. He leads the Minnesota Natural Language Processing (NLP) group that aims to develop human-centered language technologies. He completed postdoc at the University of California, Berkeley, and obtained a Ph.D. in the Language Technologies Institute of the School of Computer Science at Carnegie Mellon University. He has been recently awarded the 3M NTFA faculty award, Sony Research faculty award, and the best paper award by the In2Writing workshop at ACL 2022. His Ph.D study was supported by the AI2 fellowship, CMU Presidential fellowship, and ILJU Ph.D fellowship