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

Author(s)/Creator(s)

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

Document Type

Article

Date

2000

Keywords

CNPL, TREC-10 Question Answering Track, linguistic patterns, keywords, query analysis

Language

English

Disciplines

Library and Information Science

Description/Abstract

This paper describes the retrieval experiments for the main task and list task of the TREC-10 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, 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.

Additional Information

Additional authors listed in the paper

Recommended Citation

Chen, Jiangping; Diekema, Anne R.; Taffet, Mary D.; McCracken, Nancy; and Ozgencil, Necati Ercan, "Question Answering: CNLP at the TREC-10 Question Answering Track" (2000). School of Information Studies - Faculty Scholarship. 57.
https://surface.syr.edu/istpub/57

Creative Commons License

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