A CCG-Based Version of the DisCoCat Framework
This addresses a theoretical bottleneck in compositional semantics for NLP researchers, though it appears incremental as it adapts an existing framework.
The paper tackled the limitations of the DisCoCat framework, which was restricted by pregroup grammars, by reformulating it using Combinatory Categorial Grammar (CCG) to enable broader experimentation and expressibility, resulting in a proof-of-concept conversion of 'Alice in Wonderland' into DisCoCat form.
While the DisCoCat model (Coecke et al., 2010) has been proved a valuable tool for studying compositional aspects of language at the level of semantics, its strong dependency on pregroup grammars poses important restrictions: first, it prevents large-scale experimentation due to the absence of a pregroup parser; and second, it limits the expressibility of the model to context-free grammars. In this paper we solve these problems by reformulating DisCoCat as a passage from Combinatory Categorial Grammar (CCG) to a category of semantics. We start by showing that standard categorial grammars can be expressed as a biclosed category, where all rules emerge as currying/uncurrying the identity; we then proceed to model permutation-inducing rules by exploiting the symmetry of the compact closed category encoding the word meaning. We provide a proof of concept for our method, converting "Alice in Wonderland" into DisCoCat form, a corpus that we make available to the community.