DNN has become a key model in solving NLP related problems among these years. A complex DNN network also show their outstanding performance than traditional NLP approaches. In this talk, several problems and datasets from data competition, e.g., QA, argumentation component mining, toxic message detection, rumor detection, and disease entity extraction, will be introduced. The state-of-the-art DNN networks that fit and solve the corresponding problems will also be described and discussed.
Hung-Yu Kao received the B.S. and M.S. degree in Computer Science from National Tsing Hua University in 1994 and 1996 respectively. In July 2003, he received the PhD degree from the Electrical Engineering Department, National Taiwan University. He is currently the Director of Institute of Medical Informatics (IMI) and Department of Computer Science and Information Engineering (CSIE) of National Cheng Kung University. He is also the chair of IEEE CIS Tainan Chapter. He was a post-doctoral fellow of Institute of Information Science (IIS), Academia Sinica from 2003 to 2004. His research interests include Web information retrieval / extraction, search engine, knowledge management, data mining, social network analysis and bioinformatics. He has published more than 60 research papers in refereed international journals and conference proceedings. He is a member of IEEE and ACM.