DeepThought



Publications

Techn. Documents
                           

Hybrid Deep and Shallow Methods for Knowledge-Intensive Information Extraction

The pioneering research performed in the research project DeepThought aims at demonstrating the potential of deep linguistic processing if combined with shallow methods for robustness. Classical information retrieval will be extended by high precision concept indexing and relation detection. On the basis of this novel approach the feasibility of three ambitious applications are demonstrated, namely: precise information extraction for business intelligence; email response management for customer relationship management; creativity support for document production and collective brainstorming. As a result, a technology roadmap was developed for a new generation of knowledge-intensive applications.


  • A new approach to the combination of deep and shallow linguistic processing.
  • Multilinguality: German, English, Italian, Norwegian, Japanese.
  • Information extraction for business intelligence.
  •  Email response management.
  • Creativity support for document production and collective brainstorming.

Sponsor:

European Commission (Project N° IST-2001-37836)

Principal Investigator:

Prof. Dr. Hans Uszkoreit

Consortium:

Saarland University
University of Sussex
University of Cambridge
Norges Teknisk-Naturvitenskapelige Universitet NTNU, CELI S.R.L.
XtraMind Technologies GmbH

DFKI GmbH
CSLI Stanford
acrolinx GmbH


Contact:

Dr. Melanie Siegel

Phone:

+49-681-302-5288

Fax:

+49-681-302-5338

Email:

siegel@dfki.de

Project Website:

http://www.dfki.de/deepthought