Document Type

Article

Date

2000

Embargo Period

1-4-2011

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

Creative Commons License


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