Word sense disambiguation with specification marks in unrestricted texts

The authors present a method for the automatic disambiguating of nouns in English texts, using the notion of specification marks and employing the noun taxonomy of the WordNet lexical knowledge base (G.A. Miller et al., 1990). The method resolves the lexical ambiguity of nouns in any sort of text, and although it relies on the semantic relations (Hypernymy and Hyponymy) and the hierarchic organization of WordNet, it does not, however, require any sort of training process, no hand-coding of lexical entries, nor the hand-tagging of texts. An evaluation of the method was done on both the Semantic Concordance Corpus (Semcor) (G.A. Miller et al., 1993), and on Microsoft's electronic encyclopaedia ("Microsoft 98 Encarta Encyclopaedia Deluxe"). The percentage of correct resolutions achieved with these two corpora were: Semcor 65.8% and Microsoft 65.6%. Such results suggest that our proposed method is quite a stable one.