2021
DOI: 10.32408/compositionality-3-4
|View full text |Cite
|
Sign up to set email alerts
|

Language Modeling with Reduced Densities

Abstract: 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 fini… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(9 citation statements)
references
References 30 publications
0
9
0
Order By: Relevance
“…To determine whether [h red , h blue ](c) is empty or not, let's look closer at the functions in (2). The product is computed pointwise, and thus the domain For example, if c is the expression French flag, then there exists a unique natural transformation from h c × h red to h blue if every text that contains both French flag and red as subtexts, also contains blue and so [h red , h blue ](French flag) = * .…”
Section: Cartesian Closurementioning
confidence: 99%
See 3 more Smart Citations
“…To determine whether [h red , h blue ](c) is empty or not, let's look closer at the functions in (2). The product is computed pointwise, and thus the domain For example, if c is the expression French flag, then there exists a unique natural transformation from h c × h red to h blue if every text that contains both French flag and red as subtexts, also contains blue and so [h red , h blue ](French flag) = * .…”
Section: Cartesian Closurementioning
confidence: 99%
“…Before going on to the next section, we briefly comment on the work in [2]. In that paper, a [0, 1]-enriched functor is defined between the syntax category L and another [0, 1]-enriched category, embedding L as subcategory of a [0, 1]-enriched category D consisting of "density" operators.…”
Section: Definitionmentioning
confidence: 99%
See 2 more Smart Citations
“…Other applications of density matrices in NLP include modelling entailment in a compositional setting (Balkir et al, 2015;Bankova et al, 2018;Lewis, 2019a;Bradley and Vlassopoulos, 2020). Blacoe et al (2013) also use density matrices to model ambiguity, but in a different setting.…”
Section: Representing Words With Density Matricesmentioning
confidence: 99%