Spoken Dialogue System based on Incremental Language Understanding and Knowledge Acquisition

September 24, 2019
Versione stampabile

Date&Time: September 24, 2019 at 12 pm
Venue: Via Sommarive 5 - Polo Ferrari 1 (Povo, TN) Room Garda


  • Koichiro Yoshino, Nara Institute of Science and Technology (NAIST)


Most of the recent dialogue systems are based on pre-defined ontology and turn-based dialogue management. However, a new framework based on incremental processing and general language understanding framework are required to realize a natural interaction with users. We propose a language understanding framework based on event embedding, embedding expression based on a predicate-argument structure for building an open-domain information navigation dialogue systems. The event-based language understanding makes it possible to build more argumentative and knowledge grounded dialogue systems. Moreover, we also built an incremental language understanding framework toward natural
communication between users and systems.

About the Speaker

Koichiro Yoshino received his B.A. degree in 2009 from Keio University, M.S. degree in informatics in 2011, and Ph.D. degree in informatics in 2014 from Kyoto University, respectively. From 2014 to 2015, he was a research fellow (PD) of Japan Society for Promotion of Science. From 2015 to 2016, he was a research assistant professor of the Graduate School of Information Science, Nara Institute of Science and Technology (NAIST). Currently, he is an assistant professor of NAIST. He is also a researcher of PRESTO, JST, concurrently. He is working on areas of spoken and natural language processings, especially on spoken dialogue systems. Dr. Koichiro Yoshino received the JSAI SIG-research award in 2013. He is a member of IEEE, SIGDIAL, ACL, IPSJ, ANLP and RSJ.

Contact: Prof. giuseppe.riccardi [at] unitn.it (Giuseppe Riccardi)