4. Semantic Analysis of Textual Input

  1. Ron S. Kenett PhD, BSc Chairman CEO Research Professor Professor Associate Director Editor in Chief President4,5 and
  2. Yossi Raanan PhD, BSc Senior Consultant Strategic Partner Senior Lecturer former dean head chairman director6,7
  1. Horacio Saggion PhD Research Fellow member1,
  2. Thierry Declerck MA Senior Consultant2 and
  3. Kalina Bontcheva PhD Senior Researcher3

Published Online: 19 AUG 2010

DOI: 10.1002/9780470972571.ch4

Operational Risk Management

Operational Risk Management

How to Cite

Saggion, H., Declerck, T. and Bontcheva, K. (2010) Semantic Analysis of Textual Input, in Operational Risk Management (eds R. S. Kenett and Y. Raanan), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9780470972571.ch4

Editor Information

  1. 4

    KPA Ltd, Raanana, Israel; University of Turin, Italy

  2. 5

    NYU-Poly, Center for Risk Engineering, New York, USA

  3. 6

    KPA Ltd, Raanana, Israel

  4. 7

    College of Management, Academic Studies, Rishon Lezion, Israel

Author Information

  1. 1

    Department of Computer Science, University of Sheffield, UK

  2. 2

    Institute of Natural Language Processing (IMS) in Stuttgart, Germany

  3. 3

    Natural Language Processing Laboratory, University of Sheffield, UK

Publication History

  1. Published Online: 19 AUG 2010
  2. Published Print: 22 OCT 2010

ISBN Information

Print ISBN: 9780470747483

Online ISBN: 9780470972571



  • business intelligence (BI);
  • General Architecture for Text Engineering (GATE);
  • MUSING project;
  • natural language processing (NLP);
  • ontology-based information extraction (OBIE);
  • processing resources (PRs)


Text processing and natural language processing (NLP) techniques can be used to transform unstructured sources into structured representations suitable for analysis. This chapter describes a number of processing resources (PRs) which are general enough to start development of text-based business intelligence (BI) applications. Text analysis algorithms use ontologies in order to obtain a formal representation of and reason about their domain. Ontology-based information extraction (OBIE) has two main purposes: automatic document annotation and automatic ontology population. The chapter describes a number of processes usually applied in the field of information extraction (IE), illustrating them with the General Architecture for Text Engineering (GATE) system, an open platform implemented in Java used worldwide in various projects, including the business intelligence MUSING project.

Controlled Vocabulary Terms

business forecasting; business intelligence (BI)