4LEX : a Multilingual Lexical resource

As the creation of computational (verb) lexicons is a huge time-consuming task, tagged corpora appear to be a very useful resource for inducing verb knowledge. In this paper we present a multilingual verb lexicon with syntactic and semantic information for four languages. For three of them (Catalan, Basque and Spanish) this lexicon is induced from syntactically and semantically annotated corpora created at the 3LB project; for Russian, the lexicon will be created manually. From this information, the correspondences between syntactic functions and semantic roles among the four languages will be set up.