Research Project
Grant-in-Aid for Challenging Exploratory Research
Typical natural language processing task tries to recover human annotations by some automatic tools. However, it is still difficult to generate sentences. In addition, most tools assume written language, which performance decrease when applied to spoken language. I dare limit our system model to fail like humans. Based on our psychologically plausible model, I build a syntactic parser with semantic analysis extention. I evaluated my system by applying to automatic dectection of dialog breakdowns, dialog system for AI werewolf agents, etc.
All 2017 2016 2015
All Journal Article (1 results) Presentation (13 results) (of which Int'l Joint Research: 1 results) Book (4 results)
Journal of Information Processing and Management
Volume: 59 Issue: 10 Pages: 658-665
10.1241/johokanri.59.658
130005180783