Corpus ID: 220404607

Language Modeling with Reduced Densities

@article{Bradley2020LanguageMW,
  title={Language Modeling with Reduced Densities},
  author={T. Bradley and Yiannis Vlassopoulos},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.03834}
}
We present a framework for modeling words, phrases, and longer expressions in a natural language using reduced density operators. We show these operators capture something of the meaning of these expressions and, under the Loewner order on positive semidefinite operators, preserve both a simple form of entailment and the relevant statistics therein. Pulling back the curtain, the assignment is shown to be a functor between categories enriched over probabilities. 

Figures from this paper

Modelling Lexical Ambiguity with Density Matrices
An enriched category theory of language: from syntax to semantics

References

SHOWING 1-10 OF 45 REFERENCES
Language as a matrix product state
Random Language Model.
  • E. DeGiuli
  • Computer Science, Medicine
  • Physical review letters
  • 2019
Tensor network language model
Graded Entailment for Compositional Distributional Semantics
Mathematical Foundations for a Compositional Distributional Model of Meaning
Modeling Sequences with Quantum States: A Look Under the Hood
...
1
2
3
4
5
...