tailieunhanh - Báo cáo khoa học: "Question Answering by Lexical Fabric and External Resources"

One of the major challenges in TRECstyle question-answering (QA) is to overcome the mismatch in the lexical representations in the query space and document space. This is particularly severe in QA as exact answers, rather than documents, are required in response to questions. Most current approaches overcome the mismatch problem by employing either data redundancy strategy through the use of Web or linguistic resources. This paper investigates the integration of lexical relations and Web knowledge to tackle this problem. The results obtained on TREC11 QA corpus indicate that our approach is both feasible and effective. . | QUALIFIER Question Answering by Lexical Fabric and External Resources Hui Yang Department of Computer Science National University of Singapore 3 Science Drive 2 Singapore 117543 yangh@ Tat-Seng Chua Department of Computer Science National University of Singapore 3 Science Drive 2 Singapore 117543 chuats@ Abstract One of the major challenges in TREC-style question-answering QA is to overcome the mismatch in the lexical representations in the query space and document space. This is particularly severe in QA as exact answers rather than documents are required in response to questions. Most current approaches overcome the mismatch problem by employing either data redundancy strategy through the use of Web or linguistic resources. This paper investigates the integration of lexical relations and Web knowledge to tackle this problem. The results obtained on TREC11 QA corpus indicate that our approach is both feasible and effective. 1 Introduction Open domain Question Answering QA is an information retrieval paradigm that is attracting increasing attention from the information retrieval IR information extraction IE and natural language processing NLP communities AAAI Spring Symposium Series 2002 ACL-EACL 2002 . A QA system retrieves concise answers to open-domain natural language questions where a large text collection termed the QA corpus is used as the source for these answers. Contrary to traditional IR tasks it is not acceptable for a QA system to retrieve a full document or a paragraph in response to a question. Contrary to traditional IE tasks no prespecified domain restrictions are placed on the questions which may be of any type and in any topic. Modem QA systems must therefore combine the strengths of traditional IR and NLP IE to provide an apposite way to answering questions. The QA task in the TREC conference series Voorhees 2002 has motivated much of the recent works focusing on fact-based short-answer questions. Examples of such .