ICADL 2007 - LNCS 4822

Towards a Hierarchical Framework for Predicting the Best Answer in a Question Answering System

Mohan John Blooma, Alton Yeow-Kuan Chua, Dion Hoe-Lian Goh, and Zhiquan Ling

Division of Information Studies, Wee Kim Wee School of Communication & Information, Nanyang Technological University
bl0002hn@ntu.edu.sg
AltonChua@ntu.edu.sg
ashlgoh@ntu.edu.sg
ling0032@ntu.edu.sg

Abstract. This research aims to develop a model for identifying predictive variables for the selection of the best quality answer in a question-answering (QA) system. It was found that accuracy, completeness and relevance are strong predictors of the quality of the answer.

Keywords: Question answering systems, Answer quality, Information Retrieval, Multiple Regression, Prediction model

LNCS 4822, p. 497 f.

Full article in PDF | BibTeX