Functorial Language Models
arXiv:2103.14411
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.
arXiv commentSubmitted to SemSpace 2021
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Mathematical Foundations for a Compositional Distributional Model of Meaning
- DisCoPy: Monoidal Categories in Python
- Foundations for Near-Term Quantum Natural Language Processing
- Autonomization of Monoidal Categories
- Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics
- Incremental Monoidal Grammars