Analysis of lexical ambiguity in Modern Greek using a computational lexicon

摘要

Ambiguity is one of the most significant problems in Natural Language Processing. This difficulty may not be apparent to native speakers because of their natural ability at resolving it using contextual information and common sense knowledge. In contrast, current computer applications are still lacking the ability to disambiguate complex texts efficiently. The most common type of ambiguity is lexical ambiguity, and this is noticed even in highly inflectional languages such as Greek. In the present article, all the patterns of predictable lexical ambiguity in Modern Greek Language are registered, verified and quantified as occurred in the Neurolingo computational lexicon, after a study of morpho-syntactic characteristics that differentiate the ambiguous words.