Extraction of how-to type question-answering sentences using query sets

Authors:
Kyohei Ishikawa;Hayato Ohwada
Affiliations:
Department of Industrial Administration, Faculty Of Science and Technology, Tokyo University of Science, Noda-shi, Chiba-ken, Japan;Department of Industrial Administration, Faculty Of Science and Technology, Tokyo University of Science, Noda-shi, Chiba-ken, Japan
Venue:
PKAW'12 Proceedings of the 12th Pacific Rim conference on Knowledge Management and Acquisition for Intelligent Systems
Year:
2012

Citing 1
Cited 0

Identifying and improving retrieval for procedural questions

Information Processing and Management: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we describe how to extract a sentence which serves as a correct answer for a how-to question about actions to be taken on the Web. The distinguishing feature of this study is the extraction of sentences using a set of queries, after collecting queries considered to be effective for answer extraction. By using a query set, it is possible to extract the answer considered to express the contents of the Web page pertinent to the question. In the results of the experiment, the average recall was 77.3% and the average precision was 62.9%.