Research in Text Processing

Abstract

SRI's DARPA-sponsored project on text processing has consisted of a broad range of efforts, from near-term practical system implementation to advanced theoretical research. The research in this project was carried out between September 1990 and November 1992. We have distinguished two distinct text processing tasks: information extraction and text understanding. In information extraction, Only a fraction of the text is relevant; in the case of the MUC-4 terrorist reports, probably only about 10% of the text is relevant. Information is mapped into a predefined, relatively simple, rigid target representation; this condition holds whenever entry of information into a database is the task. The subtle nuances of meaning and the writer's goals in writing the text are of no interest.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 21, 1992
Accession Number
ADA259434

Entities

People

  • Jerry R. Hobbs

Organizations

  • SRI International

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Automata
  • Cognitive Science
  • Computational Linguistics
  • Computer Science
  • Construction
  • Databases
  • Grammars
  • Hash Tables
  • Language
  • Linguistics
  • Machine Translation
  • Natural Language Processing
  • Natural Languages
  • Reasoning
  • Recognition
  • Terrorists

Readers

  • Computational Linguistics
  • Systems Analysis and Design
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval