Question-Answering: CNLP at TREC-10 Question Answering Track

Document Type

Conference Paper

Journal/Book Title/Conference

Text Retrieval Conference


E.M. Voorhees and D.K. Harman


Center for Natural Language Processing

Publication Date



This paper describes the retrieval experiments for the main task and list task of the TREC-10 questionanswering track. The question answering system described automatically finds answers to questions in a large document collection. The system uses a two-stage retrieval approach to answer finding based on matching of named entities, linguistic patterns, and keywords. In answering a question, the system carries out a detailed query analysis that produces a logical query representation, an indication of the question focus, and answer clue words.


Originally published by the Center for Natural Language Processing (CNLP). Publisher's PDF available through remote link. Must click on corresponding article.