Computational approaches for studying proverbs

Starting with the presupposition that a methodology and a system of classification are vital elements to the description of proverbs, this paper intends to provide a contribution to the study of proverbs. A computational approach based on tools as electronic lexical databases and ontology is presented. The aim of this paper is the semi automatic annotation of Italian and Spanish proverbs, using MultiWordNet resource, and the construction of a conceptual domain-specific model in order to extract the semantics. MultiWordNet, a multilingual lexical database, constitutes a large coverage sense inventory which is the basis for semantic tagging. It can be seen as an ontology to be used for a variety of knowledge-based natural language processing tasks. The work of this paper is a significant step toward a semantic annotation, a basic technology for intelligent content management. This experiment may contribute to deepen knowledge about “linguistic culture” and to facilitate the correlation among classes of proverbs.