Résumé
Type-theoretic frameworks for compositional semantics are aimed at producing structured meaning representations of natural language utterances.<br />Using elements of lexical semantics, these frameworks are able to model many complex phenomena related to the polysemy of words and their context-dependent meanings. However, they are just as powerful as the lexical resources they can access. This paper explores ways to create and enrich wide-coverage, weighted lexical resources from crowd-sourced data. Specifically, we investigate how existing rich lexical networks – created and validated by serious games – can be used to infer linguistic coercions along with ranking corresponding to preferences in their interpretations.