Template Design for Information Extraction

Abstract

The design of the template for an information extraction application (or exercise) reflects the nature of the task and therefore crucially affects the success of the attempt to capture information from text. This paper addresses the template design requirement by discussing the general principles or desiderata of template design, object-oriented vs. flat template design, and template definition notation, all reflecting the results and lessons learned in the TIPSTER/MUC-5 template definition effort which is explicitly discussed in a Case Study in the last section of this paper.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1993
Accession Number
ADA630833

Entities

People

  • Boyan Onyshkevych

Organizations

  • United States Department of Defense

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Case Studies
  • Databases
  • Department Of Defense
  • Elements
  • Extraction
  • Governments
  • Human-Machine Interfaces
  • Information Operations
  • Language
  • Lessons Learned
  • Notation
  • Removal
  • Specifications
  • Standards
  • Template Patterns

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Business Analytics
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation