A CCG-Based Version of the DisCoCat Framework

Richie Yeung, Dimitri Kartsaklis


Abstract
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.
Anthology ID:
2021.semspace-1.3
Volume:
Proceedings of the 2021 Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science (SemSpace)
Month:
June
Year:
2021
Address:
Groningen, The Netherlands
Editors:
Martha Lewis, Mehrnoosh Sadrzadeh
Venue:
SemSpace
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
20–31
Language:
URL:
https://aclanthology.org/2021.semspace-1.3
DOI:
Bibkey:
Cite (ACL):
Richie Yeung and Dimitri Kartsaklis. 2021. A CCG-Based Version of the DisCoCat Framework. In Proceedings of the 2021 Workshop on Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science (SemSpace), pages 20–31, Groningen, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
A CCG-Based Version of the DisCoCat Framework (Yeung & Kartsaklis, SemSpace 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semspace-1.3.pdf