https://scholars.lib.ntu.edu.tw/handle/123456789/413132
標題: | Modeling human inference process for textual entailment recognition | 作者: | Huang H.-H. Chang K.-C. Chen H.-H. |
公開日期: | 2013 | 卷: | 2 | 起(迄)頁: | 446-450 | 來源出版物: | 51st Annual Meeting of the Association for Computational Linguistics | 摘要: | 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 dataset and Chinese NTCIR-9 RITE dataset, and conclude the same findings. ? 2013 Association for Computational Linguistics. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413132 | ISBN: | 9781937284510 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。