This paper summarizes IRST’s participation in Senseval-3. We participated both in the English allwords task and in some lexical sample tasks (English, Basque, Catalan, Italian, Spanish). We followed two perspectives. On one hand, for the allwords task, we tried to refine the Domain Driven Disambiguation that we presented at Senseval-2. The refinements consist of both exploiting a new technique (Domain Relevance Estimation) for domain detection in texts, and experimenting with the use of Latent Semantic Analysis to avoid reliance on manually annotated domain resources (eg WORDNET DOMAINS). On the other hand, for the lexical sample tasks, we explored the direction of pattern abstraction and we demonstrated the feasibility of leveraging external knowledge using kernel methods.