A Hybrid Relational Approach for Word Sense Disambiguation

We propose a novel approach for word sense disambiguation which makes use of corpus-based evidence combined with background knowledge. Using an inductive logic programming technique, it generates expressive models which exploit several knowledge sources and also the relations between them. The approach is evaluated in two tasks: identification of the correct translation for verbs in English-Portuguese and disambiguation of verbs from the Senseval-3 competition. The accuracy obtained in the multilingual task outperforms the alternative learning techniques investigated. The models also yielded significant improvement to the translation quality when integrated into a machine translation system. In the monolingual task, the approach performs as well as the state-of-theart systems for Senseval verbs.