Abstract
Traditional Chinese text retrieval systems return a ranked list of documents in response to a user's request. While a ranked list of documents may be an appropriate response for the user, frequently it is not. Usually it would be better for the system to provide the answer itself instead of requiring the user to search for the answer in a set of documents. Since Chinese text retrieval has just been developed lately, and due to various specific characteristics of Chinese language, the approaches to its retrieval are quite different from those studies and researches proposed to deal with Western language. Thus, an architecture that augments existing search engines is developed to support Chinese natural language question answering. In this paper a new approach to building Chinese question-answering system is described, which is the general-purpose, fully-automated Chinese question-answering system available on the web. In the approach, we attempt to represent Chinese text by its characteristics, and try to convert the Chinese text into ERE (E: entity, R: Relation) relation data lists, and then to answer the question through ERE relation model. The system performs quite well giving the simplicity of the techniques being utilized. Experimental results show that question-answering accuracy can be greatly improved by analyzing more and more matching ERE relation data lists. Simple ERE relation data extraction techniques work well in our system making it efficient to use with many backend retrieval engines.
Similar content being viewed by others
References
Sanda M Harabagiu, Vinay Chaudhri. Mining answers from text and knowledge bases.AAAI Spring Symposium Series, American, 2002.
Workshop on Open-domain Question Answering.ACLEACL, USA, 2002.
Voorhees E, Harman D (eds.). Overview of the Ninth text retrieval conference. InProc. the Ninth Text Retrieval Conference (TREC-9), NIST Special Publication, Gaithersburg, Maryland, 2000, pp.1–13.
Voorhees E, Harman D (eds.). Overview of TREC 2001. InProc. the Tenth Text Retrieval Conference (TREC 2001), NIST Special Publication, Gaithersburg, Maryland, 2001, pp.1–15.
Voorhees E. The Trec-8 question answering track report. InProc. TREC-8, Gaithersburg, Maryland, 1999, pp.77–82.
Gai-Tai Huang, Hsiu-Hsen Yao. Chinese text information extraction based on conceptual schema.International Conference on Chinese Computing-Learning. Singapore, 2001, pp.242–249.
Voorhees E, Tice D. The TREC-8 question answering track evaluation. InProc. TREC-8, Gaithersburg, Maryland, 1999, pp.83–105.
Radev D B, Libner K, Fan W. Getting answers to natural language queries on the web.Journal of the American Society for Information Science and Technology (JASIST), 2002, 53(5): 359–364.
Kwok C, Etzioni O, Weld D. Scaling question answering to the Web. InProc. the 10th World Wide Web Conference (WWW′10) Hong Kong, 2001, pp.150–161.
Eugene Agichtein, Steve Lawrence, Luis Gravano. Learning search engine specific query transformations for question answering. InProc. the 10th World Wide Web Conference (WWW 2001), Hong Kong, 2001, pp.169–178.
Eric J Glover, Gary W Flake, Steve Lawrenceet al. Improving category specific web search by learning query modifications. InProc. Symposium on Applications and the Internet, SAINT, 2001, San Diego, California, 2001, pp.23–34.
Dragomir Radev, Weiguo Fan, Hong Qiet al. Probabilistic Question Answering on the Web.WWW2002, Honolulu, Hawaii, USA, May 711, 2002, pp.408–419.
Wan Jiancheng, Yao Wenlin. Chinese syntactic and semantic analysis based on binary relations.Communications of COLIPS, 1998, 8: 31–42.
Li Sujianet al. Semantic computation in a Chinese question-answering system.Journal of Computer Science & Technology, Nov. 2002, 17(6): 933–939.
Search engine. Available at http://www.google.com.
Newspaper web site. Available at http://news.chinatimes.com/
Medical web site. Available at http://www.icareasia.com/
Chinese dictionary developed by Academia Sinica. Available at http://godel.iis.sinica.edu.tw/CKIP/r_content.htm
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, GT., Yao, HH. Chinese question-answering system. J. Compt. Sci. & Technol. 19, 479–488 (2004). https://doi.org/10.1007/BF02944749
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02944749