English

Functorial Language Models

Computation and Language 2021-03-29 v1 Category Theory

Abstract

We introduce functorial language models: a principled way to compute probability distributions over word sequences given a monoidal functor from grammar to meaning. This yields a method for training categorical compositional distributional (DisCoCat) models on raw text data. We provide a proof-of-concept implementation in DisCoPy, the Python toolbox for monoidal categories.

Keywords

Cite

@article{arxiv.2103.14411,
  title  = {Functorial Language Models},
  author = {Alexis Toumi and Alex Koziell-Pipe},
  journal= {arXiv preprint arXiv:2103.14411},
  year   = {2021}
}

Comments

Submitted to SemSpace 2021