Tai-Danae Bradley ; Yiannis Vlassopoulos - Language Modeling with Reduced Densities

compositionality:13514 - Compositionality, November 30, 2021, Volume 3 (2021) - https://doi.org/10.32408/compositionality-3-4
Language Modeling with Reduced DensitiesArticle

Authors: Tai-Danae Bradley ORCID1,2; Yiannis Vlassopoulos 3

This work originates from the observation that today's state-of-the-art statistical language models are impressive not only for their performance, but also - and quite crucially - because they are built entirely from correlations in unstructured text data. The latter observation prompts a fundamental question that lies at the heart of this paper: What mathematical structure exists in unstructured text data? We put forth enriched category theory as a natural answer. We show that sequences of symbols from a finite alphabet, such as those found in a corpus of text, form a category enriched over probabilities. We then address a second fundamental question: How can this information be stored and modeled in a way that preserves the categorical structure? We answer this by constructing a functor from our enriched category of text to a particular enriched category of reduced density operators. The latter leverages the Loewner order on positive semidefinite operators, which can further be interpreted as a toy example of entailment.


Volume: Volume 3 (2021)
Published on: November 30, 2021
Imported on: May 2, 2024
Keywords: Computer Science - Computation and Language,Computer Science - Machine Learning,Mathematics - Category Theory,Quantum Physics

3 Documents citing this article

Consultation statistics

This page has been seen 6 times.
This article's PDF has been downloaded 9 times.