Welcome to the InfoSci Platform
Reference Hub5
Toward Automatic Answers in User-Interactive Question Answering Systems

Toward Automatic Answers in User-Interactive Question Answering Systems

Tianyong Hao, Feifei Xu, Jingsheng Lei, Liu Wenyin, Qing Li
Copyright: © 2011 |Volume: 3 |Issue: 4 |Pages: 15
ISSN: 1942-9045|EISSN: 1942-9037|EISBN13: 9781613509203|DOI: 10.4018/jssci.2011100104
Cite Article Cite Article

MLA

Hao, Tianyong, et al. "Toward Automatic Answers in User-Interactive Question Answering Systems." IJSSCI vol.3, no.4 2011: pp.52-66. http://doi.org/10.4018/jssci.2011100104

APA

Hao, T., Xu, F., Lei, J., Wenyin, L., & Li, Q. (2011). Toward Automatic Answers in User-Interactive Question Answering Systems. International Journal of Software Science and Computational Intelligence (IJSSCI), 3(4), 52-66. http://doi.org/10.4018/jssci.2011100104

Chicago

Hao, Tianyong, et al. "Toward Automatic Answers in User-Interactive Question Answering Systems," International Journal of Software Science and Computational Intelligence (IJSSCI) 3, no.4: 52-66. http://doi.org/10.4018/jssci.2011100104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A strategy of automatic answer retrieval for repeated or similar questions in user-interactive systems by employing semantic question patterns is proposed in this paper. The used semantic question pattern is a generalized representation of a group of questions with both similar structure and relevant semantics. Specifically, it consists of semantic annotations (or constraints) for the variable components in the pattern and hence enhances the semantic representation and greatly reduces the ambiguity of a question instance when asked by a user using such pattern. The proposed method consists of four major steps: structure processing, similar pattern matching and filtering, automatic pattern generation, question similarity evaluation and answer retrieval. Preliminary experiments in a real question answering system show a precision of more than 90% of the method.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.