首页 | 本学科首页   官方微博 | 高级检索  
     

Automatic Question Answering from Web Documents
引用本文:LI Xin HU Dawei LI Huan HAO Tianyong CHEN Enhon LIU Wenyin. Automatic Question Answering from Web Documents[J]. 武汉大学学报:自然科学英文版, 2007, 12(5): 875-880. DOI: 10.1007/s11859-007-0046-4
作者姓名:LI Xin HU Dawei LI Huan HAO Tianyong CHEN Enhon LIU Wenyin
作者单位:[1]Department of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, Anhui, China [2]Department of Computer Science, City University of Hong Kong, Hong Kong, China [3]Joint Research Laboratory of Excellence, CityU- USTC Advanced Research Institute, Suzhou 215123, Jiangsu, China
基金项目:Supported by the National Basic Research Program of China (2003CB317002) and the Grant from City University of Hong Kong (7002137)
摘    要:A passage retrieval strategy for web-based question answering (QA) systems is proposed in our QA system. It firstly analyzes the question based on semantic patterns to obtain its syntactic and semantic information and then form initial queries. The queries are used to retrieve documents from the World Wide Web (WWW) using the Google search engine. The queries are then rewritten to form queries for passage retrieval in order to improve the precision. The relations between keywords in the question are employed in our query rewrite method. The experimental result on the question set of the TREC-2003 passage task shows that our system performs well for factoid questions.

关 键 词:询问应答 通道修复 语义模式 语义信息
文章编号:1007-1202(2007)05-0875-06
收稿时间:2007-03-03
修稿时间:2007-03-03

Automatic question answering from Web documents
Li Xin,Hu Dawei,Li Huan,Hao Tianyong,Chen Enhong,Liu Wenyin. Automatic question answering from Web documents[J]. Wuhan University Journal of Natural Sciences, 2007, 12(5): 875-880. DOI: 10.1007/s11859-007-0046-4
Authors:Li Xin  Hu Dawei  Li Huan  Hao Tianyong  Chen Enhong  Liu Wenyin
Affiliation:(1) Department of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, Anhui, China;(2) Department of Computer Science, City University of Hong Kong, Hong Kong, China;(3) Joint Research Laboratory of Excellence, CityU-USTC Advanced Research Institute, Suzhou, 215123, Jiangsu, China
Abstract:A passage retrieval strategy for web-based question answering (QA) systems is proposed in our QA system. It firstly analyzes the question based on semantic patterns to obtain its syntactic and semantic information and then form initial queries. The queries are used to retrieve documents from the World Wide Web (WWW) using the Google search engine. The queries are then rewritten to form queries for passage retrieval in order to improve the precision. The relations between keywords in the question are employed in our query rewrite method. The experimental result on the question set of the TREC-2003 passage task shows that our system performs well for factoid questions. Biography: LI Xin (1982–), male, Ph. D. candidate, research direction: question answering system, information retrieval, data mining.
Keywords:question answering(QA)  passage retrieval  semantic pattern
本文献已被 维普 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号