Language-independence of DisCoCirc's Text Circuits: English and Urdu
Abstract
DisCoCirc is a newly proposed framework for representing the grammar and semantics of texts using compositional, generative circuits. While it constitutes a development of the Categorical Distributional Compositional (DisCoCat) framework, it exposes radically new features. In particular, [14] suggested that DisCoCirc goes some way toward eliminating grammatical differences between languages. In this paper we provide a sketch that this is indeed the case for restricted fragments of English and Urdu. We first develop DisCoCirc for a fragment of Urdu, as it was done for English in [14]. There is a simple translation from English grammar to Urdu grammar, and vice versa. We then show that differences in grammatical structure between English and Urdu - primarily relating to the ordering of words and phrases - vanish when passing to DisCoCirc circuits.
Cite
@article{arxiv.2208.10281,
title = {Language-independence of DisCoCirc's Text Circuits: English and Urdu},
author = {Muhammad Hamza Waseem and Jonathon Liu and Vincent Wang-Maścianica and Bob Coecke},
journal= {arXiv preprint arXiv:2208.10281},
year = {2022}
}
Comments
In Proceedings E2ECOMPVEC, arXiv:2208.05313