Question Answering: CNLP at the TREC-2002 Question Answering Track

Author(s)/Creator(s)

Anne R. Diekema, Syracuse University
Jiangping Chen, Syracuse UniversityFollow
Nancy McCracken, Syracuse UniversityFollow
Necati Ercan Ozgencil, Syracuse University
Mary D. Taffet, Syracuse University

Document Type

Article

Date

2002

Keywords

information retrieval, TREC-2002, query representation, question answering, reference

Disciplines

Library and Information Science

Description/Abstract

This paper describes the retrieval experiments for the main task and list task of the TREC-2002 question-answering 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, keywords, and the use of a new inference module. 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.

Additional Information

Other authors include:

Ozgur Yilmazel, Syracuse University

Elizabeth D. Liddy, Syracuse University

Recommended Citation

Diekema, Anne R.; Chen, Jiangping; McCracken, Nancy; Ozgencil, Necati Ercan; and Taffet, Mary D., "Question Answering: CNLP at the TREC-2002 Question Answering Track" (2002). School of Information Studies - Faculty Scholarship. 112.
https://surface.syr.edu/istpub/112

Source

local input

Creative Commons License

This work is licensed under a Creative Commons Attribution 3.0 License.