Generating personalized answers by constructing a question situation

Authors:
Yanwen Wu;Zhenghong Wu;Yan Li;Jinling Li
Affiliations:
Department of Information & Technology, Central China Normal University, Wuhan, China;Department of Information & Technology, Central China Normal University, Wuhan, China;Department of Information & Technology, Central China Normal University, Wuhan, China;Department of Information & Technology, Central China Normal University, Wuhan, China
Venue:
ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
Year:
2005

Citing 0
Cited 1

A Question Understanding Model Based on Knowledge Points for Chinese Question Answering Service in E-Learning

ICCS '07 Proceedings of the 7th international conference on Computational Science, Part III: ICCS 2007

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper proposes a methodology to generate the personalized answer based on a question situation. To construct the question situation, personal learning characteristics should be obtained by principal component analysis and question type vector is used in the process of semantic analysis. After these analyses, the question situation is constructed based on a harmony network. The answer parameters, including answer depth and answer presentation pattern, are calculated by harmony function. According to these parameters, the personalized answer is matched by the adaptive neuro-fuzzy inference (ANFI). The system architecture of personalized answer generation is proposed in this paper and takes a learner’s question to demonstrate.