Modeling Human Inference Process for Textual Entailment Recognition

Hen-Hsen Huang, Kai-Chun Chang, Hsin-Hsi Chen
2013 Annual Meeting of the Association for Computational Linguistics  
This paper aims at understanding what human think in textual entailment (TE) recognition process and modeling their thinking process to deal with this problem. We first analyze a labeled RTE-5 test set and find that the negative entailment phenomena are very effective features for TE recognition. Then, a method is proposed to extract this kind of phenomena from text-hypothesis pairs automatically. We evaluate the performance of using the negative entailment phenomena on both the English RTE-5
more » ... taset and Chinese NTCIR-9 RITE dataset, and conclude the same findings.
dblp:conf/acl/HuangCC13 fatcat:hsndygyilfh2ddlnt6ay5q4nfq