UNT at TREC 2004: Question Answering Combining Multiple Evidences

Description:

This paper discusses Question Answering (QA) combining multiple evidences.

Creator(s):
Creation Date: 2004  
Partner(s):
UNT College of Information
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 32
Past 30 days: 2
Yesterday: 0
Creator (Author):
Chen, Jiangping

University of North Texas

Creator (Author):
Ge, He

University of North Texas

Creator (Author):
Wu, Yan

University of North Texas

Creator (Author):
Jiang, Shikun

University of North Texas

Date(s):
  • Creation: 2004
Description:

This paper discusses Question Answering (QA) combining multiple evidences.

Degree:
Note:

Abstract: This paper discusses Question Answering (QA) combining multiple evidences. QA aims at identifying answers to users' natural language questions. A QA system can release the users from digesting large amounts of text in order to locate particular facts or numbers. The research has drawn great attention from several disciplines such as information retrieval, information extraction, natural language processing, and artificial intelligence. TREC QA track has provided comparable QA system evaluation on a set of test questions since 1999. The degree of difficulty of the test questions has increased substantially in recent two years, which push the research toward applying more sophisticated strategies and better understanding of English texts. This article discusses this research.

Physical Description:

8 p.

Language(s):
Subject(s):
Keyword(s): question answering | natural language processing | information retrieval | EagleQA
Source: Thirteenth Text Retrieval Conference (TREC), 2004, Gaithersburg, Maryland, United States
Contributor(s):
Partner:
UNT College of Information
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc96842
Resource Type: Paper
Format: Text
Rights:
Access: Public