Question Answering: CNLP at the TREC-9 Question Answering Track

Author(s)/Creator(s)

Anne R. Diekema, Utah State University
Xiaoyong Liu, Syracuse University
Jiangping Chen, Syracuse UniversityFollow
Hudong Wang, Syracuse University
Nancy McCracken, Syracuse UniversityFollow

Document Type

Article

Date

2000

Keywords

CNLP, TREC-9, question answering track

Language

English

Disciplines

Library and Information Science

Description/Abstract

This paper describes a question answering system that automatically finds answers to questions in a large collection of documents. The prototype CNLP question answering system was developed for participation in the TREC-9 question answering track. The system uses a two-stage retrieval approach to answer finding based on keyword and named entity matching. Results indicate that the system ranks correct answers high (mostly rank 1), provided that an answer to the question was found. Performance figures and further analyses are included.

Additional Information

Additional authors listed in the paper

Recommended Citation

Diekema, Anne R.; Liu, Xiaoyong; Chen, Jiangping; Wang, Hudong; and McCracken, Nancy, "Question Answering: CNLP at the TREC-9 Question Answering Track" (2000). School of Information Studies - Faculty Scholarship. 56.
https://surface.syr.edu/istpub/56

Creative Commons License

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