Collecting Weighted Coercions from Crowd-Sourced Lexical Data for Compositional Semantic Analysis

摘要

Type-theoretic frameworks for compositional semantics are aimed at producing structured meaning representations of natural language utterances. 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.