Sense Equivalence in plWordNet to Princeton WordNet Mapping

Abstract

Though the interest in use of wordnets for lexicography is (gradually) growing, no research has been conducted so far on equivalence between lexical units (or senses) in inter-linked wordnets. In this paper, we present and validate a procedure of sense-linking between plWordNet and Princeton WordNet. The proposed procedure employs a continuum of three equivalence types: strong, regular and weak, distinguished by a custom-designed set of formal, semantic and translational features. To validate the procedure, three independent samples of 120 sense pairs were manually analysed with respect to the features. The results show that synsets from the two wordnets linked by interlingual synonymy relation have a greater number of equivalents than those linked through interlingual partial synonymy or interlingual hyponymy relations. Even synsets linked via interlingual synonymy may have pairs of lexical units which are only weak equivalents. More-fine grained sense linking enhances the usefulness of the mapped wordnets as a bilingual lexicon for translators or researchers.