The Use of Dynamic Segment Scoring for Language-Independent Question Answering
Abstract
This paper presents a novel language-independent question/answering (Q/A) system based on natural language processing techniques, shallow query understanding, dynamic sliding window techniques, and statistical proximity distribution matching techniques. The performance of the proposed system using the latest Text REtrieval Conference (TREC-8) data was comparable to results reported by the top TREC-8 contenders.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2001
- Accession Number
- ADA460584
Entities
People
- Clifford Weinstein
- Daniel Pack
Organizations
- Massachusetts Institute of Technology