Adaptive information extraction from unstructured documents

Csaba Dezsényi, T. Dobrowiecki, Tamás Mészáros

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The authors present a novel adaptive framework that enables efficient development of applications demanding complex document analysis. In processing natural language documents the task is to transform them into application specific structured form. Such transformation has to be designed taking into account various abstraction levels and granularity of the processing and the multitude of possibly related requests driving the application. The proposed solution is based on the adaptively planned and executed network of information processing modules. The paper presents an overview of the framework, with the focus on the adaptive mechanism. An illustrative pilot application is also provided.

Original languageEnglish
Pages (from-to)156-180
Number of pages25
JournalInternational Journal of Intelligent Information and Database Systems
Volume1
Issue number2
Publication statusPublished - 2007

Keywords

  • adaptive system
  • document analysis
  • IE
  • information extraction
  • language engineering platform

ASJC Scopus subject areas

  • Information Systems

Cite this