Information Extraction Supported Question Answering

Abstract

This paper discusses the use of our information extraction (IE) system, Textract, in the question-answering (QA) track of the recently held TREC-8 tests. One of our major objectives is to examine how IE can help IR (Information Retrieval) in applications like QA. Our study shows: (1) IE can provide solid support for QA; (2) low-level IE like Named Entity tagging is often a necessary component in handling most types of questions; (3) a robust natural language shallow parser provides a structural basis for handling questions; (4) high-level domain independent IE, i.e. extraction of multiple relationships and general events, is expected to bring about a breakthrough in QA.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 15, 1999
Accession Number
ADA460042

Entities

People

  • Rohini Srihari
  • Wei Li

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Biomedical
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Acquisition
  • Air Force
  • Air Force Research Laboratories
  • Automated Text Summarization
  • Computer Languages
  • Extraction
  • Information Retrieval
  • Language
  • Machine Learning
  • Named Entity Recognition
  • Natural Language Processing
  • Natural Languages
  • New York
  • Ontologies
  • Standards
  • United States
  • Web Browsers

Fields of Study

  • Computer science

Readers

  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval