Modeling Human Inference Process for Textual Entailment Recognition
Hen-Hsen Huang, Kai-Chun Chang and Hsin-Hsi Chen
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 2013
This paper aims at understanding what human think in textual entailment (TE) recognition process and modeling their thinking process to deal with this prob-lem. We first analyze a labeled RTE-5 test set and find that the negative entail-ment phenomena are very effective fea-tures for TE recognition. Then, a method is proposed to extract this kind of phe-nomena from text-hypothesis pairs auto-matically. 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.
Conference Manager (V2.61.0 - Rev. 2792M)