An Adaptable IE System to New Domains

  • Authors:
  • J. Turmo;N. Català;H. Rodríguez

  • Affiliations:
  • Dept. Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Espanya. turmo@lsi.upc.es;Dept. Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Espanya. ncatala@lsi.upc.es;Dept. Llenguatges i Sistemes Informàtics, Universitat Politècnica de Catalunya, Barcelona, Espanya. horacio@lsi.upc.es

  • Venue:
  • Applied Intelligence
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

The most extended way of acquiring information forknowledge based systems is to do it manually. However, the high cost of thisapproach and the availability of alternative Knowledge Sources haslead to an increasing use of automatic acquisition approaches. Inthis paper we present M-TURBIO, a Text-Based Intelligent System (TBIS)that extracts information contained in restricted-domaindocuments. The system acquires part of its knowledge about thestructure of the documents and the way the information is presented(i.e., syntactic-semantic rules) from a training set of these. Then,a database is created by means of applying thesesyntactic-semantic rules to extract the information contained in thewhole document.