Information Theory-based Compositional Distributional Semantics

Abstract In the context of text representation, Compositional Distributional Semantics models aim to fuse the Distributional Hypothesis and the Principle of Compositionality. Text embedding is based on coocurrence distributions and the representations are in turn combined by compositional functions taking into account the text structure. However, the theoretical basis of compositional functions is still an open issue. In this paper we define and study the notion of Information Theory-based Compositional Distributional Semantics (ICDS): i) We first establish formal properties for embedding, composition and similarity functions based on Shannon’s Information Theory; ii) we analyse the existing approaches under this prism, checking whether or not they comply with the established desirable properties; iii) we propose two parameterisable composition and similarity functions that generalise traditional approaches while fulfilling the formal properties; and finally iv) we perform an empirical study on several textual similarity datasets that include sentences with a high and low lexical overlap, and on the similarity between words and their description. Our theoretical analysis and empirical results show that fulfilling formal properties affects positively the accuracy of text representation models in terms of correspondence (isometry) between the embedding and meaning spaces.