Huang H.-H.Chang K.-C.Chen H.-H.2019-07-102019-07-1020139781937284510https://scholars.lib.ntu.edu.tw/handle/123456789/413132This 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 dataset and Chinese NTCIR-9 RITE dataset, and conclude the same findings. ? 2013 Association for Computational Linguistics.conference paper2-s2.0-84907354744https://www.scopus.com/inward/record.uri?eid=2-s2.0-84907354744&partnerID=40&md5=910359ccf4f9dc1913f21c00843951c5