This paper describes the exemplar based approach presented by UNED at Senseval-3. Instead of representing contexts as bags of terms and defining a similarity measure between contexts, we propose to represent terms as bags of contexts and define a similarity measure between terms. Thus, words, lemmas and senses are represented in the same space (the context space), and similarity measures can be defined between them. New contexts are transformed into this representation in order to calculate their similarity to the candidate senses. We show how standard similarity measures obtain better results in this framework. A new similarity measure in the context space is proposed for selecting the senses and performing disambiguation. Results of this approach at Senseval-3 are here reported.
[1]
Thorsten Brants,et al.
TnT – A Statistical Part-of-Speech Tagger
,
2000,
ANLP.
[2]
Lluís Màrquez i Villodre,et al.
A Comparison between Supervised Learning Algorithms for Word Sense Disambiguation
,
2000,
CoNLL/LLL.
[3]
Christiane Fellbaum,et al.
Book Reviews: WordNet: An Electronic Lexical Database
,
1999,
CL.
[4]
Nancy Ide,et al.
Introduction to the Special Issue on Word Sense Disambiguation: The State of the Art
,
1998,
Comput. Linguistics.
[5]
George A. Miller,et al.
A Semantic Concordance
,
1993,
HLT.