A Fast and Reliable Question-Answering System Based on Predictive Answer Indexing and Lexico-Syntactic Pattern Matching

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.

Download Full-text

Toward Automatic Answers in User-Interactive Question Answering Systems

International Journal of Software Science and Computational Intelligence ◽

10.4018/jssci.2011100104 ◽

2011 ◽

Vol 3 (4) ◽

pp. 52-66 ◽

Cited By ~ 5

Author(s):

Tianyong Hao ◽

Feifei Xu ◽

Jingsheng Lei ◽

Liu Wenyin ◽

Qing Li

Keyword(s):

Pattern Matching ◽

Similar Pattern ◽

Question Answering ◽

Semantic Representation ◽

Pattern Generation ◽

Interactive Systems ◽

Question Answering System ◽

Semantic Annotations ◽

Question Answering Systems ◽

Interactive Question

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.

Download Full-text

Research of ISIC-CDIO Question Answer System for Materials Teaching Based on Android

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.214.596 ◽

2012 ◽

Vol 214 ◽

pp. 596-600

Author(s):

Hui Yan ◽

Hai Yan Hu

Keyword(s):

Artificial Intelligence ◽

Wireless Network ◽

Pattern Matching ◽

Question Answering ◽

Mobile Wireless ◽

Question Answering System ◽

Cultivation Mode ◽

Similarity Algorithm ◽

Artificial Intelligence Technology ◽

The Individual

This essay innovatively proposes the education mode of ISIC-CDIO and introduces the Android mobile platform to teaching procedures by utilizing the existing mobile wireless network and artificial intelligence technology. It also realizes the question-answering system for teaching under the cultivation mode of ISIC-CDIO, focusing on two similarity algorithm- stereotyped matching and no pattern matching studying. The improvement of algorithm has increased the efficiency of successful matching of problems, which will promote the individual learning of students and thus will cultivate the comprehensive talents with ISIC-CDIO quality.

Download Full-text