[4N3-GS-6] Language media processing:

[4N3-GS-6-02] Common sense reasoning with predicate-argument PPMI third-order tensor

〇Hiroyasu Itsui¹, Kotaro Otomura¹, Hayato Uchide¹, Tatsuhiko Saito¹, Yusuke Koji¹ (1. Mitsubishi Electric Corporation, Information Technology R&D Center.)

[[Online]]

Keywords:common sense reasoning, pointwise mutual information, third-order tensor

In this research, we propose a method to acquire common sense data from a large-scale text corpus. The common sense data is calculated as predicate-argument positive pointwise mutual information (PPMI) third order tensor of a word. Specifically, we extract provisional predicates and arguments using the part-of-speech information of words, and a result of evaluating this PPMI model using the common sense reasoning benchmark set JCommonsenseQA, an accuracy of 66.0% was confirmed.