2nd International ICST Conference on Scalable Information Systems

Research Article

An Answer Passage Retrieval Strategy for Web-based Question Answering

Download534 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.4108/infoscale.2007.217,
    author={Xin Li and Dawei Hu and Tianyong Hao and Enhong Chen and Liu Wenyin},
    title={An Answer Passage Retrieval Strategy for Web-based Question Answering},
    proceedings={2nd International ICST Conference on Scalable Information Systems},
    proceedings_a={INFOSCALE},
    year={2010},
    month={5},
    keywords={Question Answering Passage Retrieval Semantic Pattern.},
    doi={10.4108/infoscale.2007.217}
}
  • Xin Li
    Dawei Hu
    Tianyong Hao
    Enhong Chen
    Liu Wenyin
    Year: 2010
    An Answer Passage Retrieval Strategy for Web-based Question Answering
    INFOSCALE
    ICST
    DOI: 10.4108/infoscale.2007.217
Xin Li1,2,3,*, Dawei Hu1,2,3,*, Tianyong Hao3,*, Enhong Chen1,2,*, Liu Wenyin2,3,*
  • 1: Department of Computer Science and Technology, University of Science & Technology of China, Hefei, China
  • 2: Joint Research Lab of Excellence, CityU-USTC Advanced Research Institute, Suzhou, China
  • 3: Department of Computer Science, City University of Hong Kong, Hong Kong, China
*Contact email: xinli@mail.ustc.edu.cn, dwhu@mail.ustc.edu.cn, tianyong@cityu.edu.hk, ehchen@ustc.edu.cn, csliuwy@cityu.edu.hk

Abstract

A passage retrieval strategy for our web-based Question Answering (QA) system is proposed in this paper. We utilize Google to retrieve web documents for answer passage finding. We propose a new method to rewrite the query for passage retrieval. We calculate the relevancy between the query and the passage by combining the term frequency and semantic relevancy. The method has been found effective in the experiment on factoid questions of TREC 2003.

Keywords
Question Answering Passage Retrieval Semantic Pattern.
Published
2010-05-16
Modified
2011-09-11
http://dx.doi.org/10.4108/infoscale.2007.217
Copyright © 2007–2024 ICST