Ontology-Based Word Sense Disambiguation in Parallel Corpora

Lately, there seems to be a growing acceptance of the idea that multilingual lexical ontologies might be the key towards aligning different views on the semantic atomic units to be used in characterizing the general meaning of various and multilingual documents. Comparing performances of word sense disambiguation systems is a difficult evaluation task when different sense inventories are used and, even more difficult when the sense distinctions are not of the same granularity. The paper substantiates this statement by presenting a statistics based system for word alignment and word sense disambiguation in parallel corpora. The system is supported by a lexical ontology made of aligned wordnets for the languages in the corpora. The wordnets are aligned via the Princeton Wordnet, used as an interlingual index. The evaluation of the WSD system was performed on the same data, using three different sense inventories.