Entailment analysis for improving Chinese textual entailment system

Author

Shih-Hung Wu ; Shan-Shun Yang ; Hung-Sheng Chiu ; Liang-Pu Chen ; Ren-Dar Yang

Author_Institution

Dept. of CSIE, Chaoyang Univ. of Technol., Taichung, Taiwan

fYear

2013

fDate

14-16 Aug. 2013

Firstpage

75

Lastpage

81

Abstract

Textual Entailment (TE) is a critical issue in natural language processing (NLP); many NLP applications can be benefited from the recognition of textual entailment (RTE). In this paper we report our observation on how to improve the Chinese textual entailment system and the experiment results on the NTCIR-10 RITE-2 dataset. To complement the traditional machine learning approach, which treat every input pair equally with the same features and the same process, our system classify different entailment cases and treat them separately. The experiment results show great improvement.

Keywords

learning (artificial intelligence); natural language processing; Chinese textual entailment system; NLP; NTCIR-10 RITE-2 dataset; RTE; entailment analysis; machine learning approach; natural language processing; recognition of textual entailment; Feature extraction; Hospitals; Natural language processing; Standards; Support vector machines; Syntactics; Training; Chinese textual entailment recognition; Entailment analysis; Textual Entailment;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Reuse and Integration (IRI), 2013 IEEE 14th International Conference on

Conference_Location

San Francisco, CA

Type

conf

DOI

10.1109/IRI.2013.6642456

Filename

6642456