• Home
  • /
  • Keynote speakers

Keynote 1: Prof. Kentaro Inui, Tohoku University, Japan

Title of talk: Natural Language Understanding and Assessment

Biography: Kentaro Inui is a Professor of the Graduate School of Information Sciences at Tohoku University, where he is head of the Natural Language Processing Lab. He also leads the Natural Language Understanding Team at the RIKEN Center for the Advanced Intelligence Project. He obtained his Ph.D. of Engineering from Tokyo Institute of Technology in 1995. His professional career started as Assistant Professor at Tokyo Institute of Technology. He then joined Kyushu Institute of Technology and Nara Institute of Science and Technology as Associate Professor in 1998 and 2002, respectively, before joining Tohoku University as Professor in 2010. He has worked on a variety of research topics in NLP, including semantic and discourse analysis, textual inference, paraphrasing, knowledge acquisition, and Web/SNS computing. For these research topics, over a span of 25 years, he has received numerous academic awards such as the COLING/ACL-2006 Best Asian NLP Paper Award, EACL-2017 Outstanding Paper Award, IBM Faculty Award (2016), PACLIC-29 Best Paper Award (2015), three Best Paper Awards from the Association for Natural Language Processing (ANLP), and sixteen Best Paper Awards at the Annual Meeting of ANLP. He has also held a variety of important positions for academic societies and conferences including Editorial Board Member of Computational Linguistics (2009-2011), Editor in Chief of Journal of Information Processing (2013-2014), and Area Chair for conferences such as ACL, EMNLP, COLING, and IJCAI. He currently serves as General Chair of EMNLP-IJCNLP 2019, Director of Association for Natural Language Processing, Member of Science Council of Japan, and Director of NPO FactCheck Initiative Japan.


Keynote 2: Prof. Danushka Bollegala, University of Liverpool, United Kingdom

Title of talk: Overcome limitations in Lexical Representations via Meta-embedding Learning

Biography: Danushka Bollegala is a Professor in the Department of Computer Science, University of Liverpool, United Kingdom, and heads the Data Mining and Machine Learning Research Group in the department. He obtained his PhD from the University of Tokyo in 2009. He then joined the University of Tokyo as an Assistant Professor before moving to UK in 2013. He has worked on various problems related to natural language processing such as text summarisation, entailment, domain adaptation, relation extraction, embedding learning and meta- embedding. He has received numerous awards for his research excellence such as the IEEE Young Author Award, conference best paper awards at GECCO and PRICAI. His research has been supported by various research council and industrial grants such as EU, DSTL, Innovate UK, JSPS, Google and MSRA. He is an Amazon Scholar.


Keynote 3: Dr. Kentaro Torisawa, Data-driven Intelligent System Research Center (DIRECT), National Institute of Information and Communications Technology (NICT), Japan

Title of talk: Two dialog systems for two extreme environments: WEKDA and SOCDA

Biography: Dr. Kentaro Torisawa graduated from the University of Tokyo in 1992. Afer receiving an MSc from the Graduate School of Science of the University of Tokyo, he became an assistant professor in the same school in 1995. In 2001, he was appointed associate professor in the School of Information Science of the Japan Advanced Institute of Science and Technology (JAIST). Since 2008, he is working at the National Institute of Information and Communications Technologies (NICT) and currently serving as the director general of the Data-Driven Intelligent Research Center (DIRECT). He has supervised the development of several large-scale NLP systems: the open-domain Japanese QA system WISDOM X, which provides answers to factoid/non-factoid questions using 4-billion web pages, and the disaster information analysis systems DISAANA and D-SUMM, which analyze tweets related to disasters in real-time and perform QA and summarization of a disaster situation using information from the analyzed tweets. These systems are now publicly available as web services and DISAANA and D-SUMM have been utilized by local governments in real disaster situations. Now, he is leading the development of the spoken dialog system WEKDA, which chats with users on a wide range of topics and gives answers to spoken factoid/non-factoid questions using deep learning technologies and 4-billion Web pages. Also he is participating in the development of another dialog system, SOCDA, which communicates with millions of disaster victims through the chat application LINE on smartphones and collects/provides disaster-related information from and to disaster victims. He has been awarded many awards/grants including the JSPS prize, the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology, the Docomo Mobile Science Award, and the Twitter Data Grants. He is also a visiting professor of the Nara Advance Institute of Science and Technology (NAIST) and a member of the Science Council of Japan.


Keynote 4 (joint with PACLING and VLSP): Tomoko Matsui, Professor, The Institute of Statistical Mathematics, Tokyo, Japan

Title: Speech processing and deep learning – the latest research development trends

Abstract: In recent years, deep learning has been used in speech processing including speaker recognition, speech recognition, speech synthesis and so on. Deep learning requires a large amount of data to estimate the massive model parameters. In particular, companies such as Google and Microsoft, which have a large amount of data and computer power to process them, are at the forefront of technology development. In this talk, some of these technologies are introduced.

Biography: Tomoko Matsui received the Ph.D. degree from the Computer Science Department, Tokyo Institute of Technology, Tokyo, Japan, in 1997. From 1988 to 2002, she was with NTT, where she worked on speaker and speech recognition. From 1998 to 2002, she was with the Spoken Language Translation Research Laboratory, ATR, Kyoto, Japan, as a Senior Researcher and worked on speech recognition. She is currently a Professor in the Institute of Statistical Mathematics, Tokyo, working on statistical modeling for a wide range of applications including speech and speaker recognition. Prof. Matsui received the paper award of the Institute of Electronics, Information, and Communication Engineers of Japan (IEICE) in 1993.