Ranking and Selecting Synsets by Domain Relevance

Paul Buitelaar, Bogdan Sacaleanu
DFKI GmbH
Stuhlsatzenhausweg 3
D66123 Saarbruecken, Germany
{paulb,bogdan}@dfki.de

Abstract
The paper presents a novel method for domain
specific sense assignment. The method
determines the domain specific relevance of
GermaNet synsets on the basis of the
relevance of their constituent terms that co-occur 
within representative domain corpora.
The approach is task independent and
completely automatic. Experiments show
results on three selected domains: business,
soccer and medical.

References
Brants, T. 2000. TnT  A Statistical Partof
Speech Tagger. In: Proceedings of 6 th ANLP
Conference, Seattle, WA.
Buitelaar, P. 2000. MUCHMORE: Multilingual
Concept Hierarchies for Medical Information
Organization and Retrieval. In: Proceedings of ASIS
2000, Chicago, USA.
Declerck, Th. and Wittenburg, P. 2001. MUMIS 
 A Multimedia Indexing and Searching Environment.
In: Proceedings of the First International Workshop
on MultiMedia Annotation, Tokyo, Japan.
Declerck, Th., Klein, J. and Neumann G. 1998.
Evaluation of the NLP Components of an Information
Extraction System for German. In: Proceedings of
LREC, Granada, Spain.
Hamp, B. and Feldweg, H. 1997. GermaNet: a
LexicalSemantic Net for German. In: Proceedings of
the ACL/EACL97 workshop on Automatic
Information Extraction and Building of Lexical
Semantic Resources for NLP Applications, Madrid.
Miller, G.A. 1995. WordNet: A Lexical Database
for English. Communications of the ACM 11.
Petitpierre, D. and Russell, G. 1995. MMORPH 
The Multext Morphology Program. Multext
deliverable report for the task 2.3.1, ISSCO,
University of Geneva.
Sacaleanu B. 2001. Domain specific Tuning and
Extension of Lexical Semantic Resources. Master
Thesis, University of the Saarland, Germany.
Salton, G. and Buckley, C. 1988. TermWeighting
Approaches In Automatic Text Retrieval. In:
Information Processing & Management. 24, 5,
pp.515523.
Turcato, D., Popowich F., Toole J., Fass D.,
Nicholson D., and Tisher G. 2000. Adapting a
synonym database to specific domains. In:
Proceedings of the ACL'2000 Workshop on Recent
Advances in Natural Language Processing and
Information Retrieval, Hong Kong.

