[3Pin1] インタラクティブ(1)

[3Pin1-16] Debating AI: Counterargument Generation Based on Textual Supportiveness Recognition

〇Misa Sato¹, Kohsuke Yanai¹, Toshihiko Yanase¹, Yuta Koreeda¹, Kenzo Kurotsuchi¹ (1. Hitachi, Ltd.)

Keywords:NLP, Argument

We will demonstrate a counterargument generation system in debating, which aims to utilize newswire articles for decision-making support. Users can specify a claim such as “We should legalize casinos because they promote economy.” and then the system outputs counterargument scripts against the claim.