[3G2] [General Session] 9. NLP / IR

[3G2-02] Textual Evidence Inference for Debating AI

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

Keywords:Natural Language Processing, Argument Mining, decision support

This paper defines textual evidence inference problem, a new NLP task for decision-making application. The objective of the textual evidence inference problem is to classify a given text into evidence categories based on a given decision-making question and a given set of sentences representing values and preferences of decision-makers. We report the technical difficulties of the problem by using newly developed dataset.