Automatic Question Answering from Web Documents

被引：3

作者：

LI XinHU DaweiLI HuanHAO TianyongCHEN EnhongLIU Wenyin Department of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei AnhuiChina Department of Computer ScienceCity University of Hong KongHong KongChina Joint Research Laboratory of ExcellenceCityUUSTC Advanced Research InstituteSuzhou JiangsuChina ^{[1
,1
,1
,2
,1
,3
,2
,3
,1
,230026
,2
,3
,215123
]}

机构：

来源：

WuhanUniversityJournalofNaturalSciences | 2007年 / 05期

关键词：

question answering(QA); passage retrieval; semantic pattern;

D O I：

暂无

中图分类号：

TP393.09 []; TP18 [人工智能理论];

学科分类号：

080402 ; 081104 ; 0812 ; 0835 ; 1405 ;

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 syn- tactic 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.

引用

页码：875 / 880

页数：6