|
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
|
|