tech,7-1-C04-1112,bq </term> . In this paper , we present a <term> corpus-based supervised word sense disambiguation ( WSD ) system </term> for <term> Dutch </term> which combines
other,17-1-C04-1112,bq disambiguation ( WSD ) system </term> for <term> Dutch </term> which combines <term> statistical classification
tech,20-1-C04-1112,bq for <term> Dutch </term> which combines <term> statistical classification ( maximum entropy ) </term> with <term> linguistic information </term>
other,27-1-C04-1112,bq classification ( maximum entropy ) </term> with <term> linguistic information </term> . Instead of building individual <term>
tech,4-2-C04-1112,bq </term> . Instead of building individual <term> classifiers </term> per <term> ambiguous wordform </term>
other,6-2-C04-1112,bq individual <term> classifiers </term> per <term> ambiguous wordform </term> , we introduce a <term> lemma-based
tech,12-2-C04-1112,bq ambiguous wordform </term> , we introduce a <term> lemma-based approach </term> . The advantage of this novel method
other,11-3-C04-1112,bq novel method is that it clusters all <term> inflected forms </term> of an <term> ambiguous word </term> in
other,15-3-C04-1112,bq all <term> inflected forms </term> of an <term> ambiguous word </term> in one <term> classifier </term> , therefore
tech,19-3-C04-1112,bq an <term> ambiguous word </term> in one <term> classifier </term> , therefore augmenting the <term> training
lr,24-3-C04-1112,bq classifier </term> , therefore augmenting the <term> training material </term> available to the algorithm . Testing
tech,2-4-C04-1112,bq available to the algorithm . Testing the <term> lemma-based model </term> on the <term> Dutch SENSEVAL-2 test
lr-prod,6-4-C04-1112,bq <term> lemma-based model </term> on the <term> Dutch SENSEVAL-2 test data </term> , we achieve a significant increase
measure(ment),17-4-C04-1112,bq achieve a significant increase in <term> accuracy </term> over the <term> wordform model </term>
tech,20-4-C04-1112,bq increase in <term> accuracy </term> over the <term> wordform model </term> . Also , the <term> WSD system based
tech,3-5-C04-1112,bq <term> wordform model </term> . Also , the <term> WSD system based on lemmas </term> is smaller and more robust . We present
skrij podrobnosti