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.

Open PDF

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

Tags

Communities of Interest

  • Air Platforms
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Data Processing
  • Extraction
  • Identification
  • Information Processing
  • Information Retrieval
  • Information Science
  • Language
  • Natural Language Processing
  • Natural Languages
  • Preprocessing
  • Second World War
  • Standards
  • Stemming
  • Translations
  • United States

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Explosive Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Translation