论文信息 - Automatic question answering from Web documents

Automatic question answering from Web documents

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.

[1] Charles L. A. Clarke,et al. Question Answering by Passage Selection (MultiText Experiments for TREC-9) , 2000, TREC.

[2] Jungyun Seo,et al. SiteQ: Engineering High Performance QA System Using Lexico-Semantic Pattern Matching and Shallow NLP , 2001, TREC.

[3] M. F. Porter,et al. An algorithm for suffix stripping , 1997 .

[4] Bernardo Magnini,et al. Is It the Right Answer? Exploiting Web Redundancy for Answer Validation , 2002, ACL.

[5] Jimmy J. Lin,et al. Quantitative evaluation of passage retrieval algorithms for question answering , 2003, SIGIR.

[6] George A. Miller,et al. WordNet: A Lexical Database for English , 1995, HLT.

[7] Jimmy J. Lin,et al. Web question answering: is more always better? , 2002, SIGIR '02.

[8] Salim Roukos,et al. IBM's Statistical Question Answering System-TREC 11 , 2001, TREC.

[9] Ellen M. Voorhees,et al. Overview of the TREC 2004 Novelty Track. , 2005 .

[10] W. Bruce Croft,et al. Passage retrieval based on language models , 2002, CIKM '02.

[11] Qingtian Zeng,et al. Semantic Pattern for User-Interactive Question Answering , 2006, SKG.

[12] James P. Callan,et al. Passage-level evidence in document retrieval , 1994, SIGIR '94.