Language as a matrix product state
Not on the map. Why?
Abstract (arXiv)
We propose a statistical model for natural language that begins by considering language as a monoid, then representing it in complex matrices with a compatible translation invariant probability measure. We interpret the probability measure as arising via the Born rule from a translation invariant matrix product state.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Nov 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 1; 2023: 0; 2024: 3.
7 papers.
- 2021Probabilistic Graphical Models and Tensor Networks: A Hybrid Frameworkcited by 5
- 2024Language Modeling Using Tensor Trainscited by 5
- 2021Tensor network to learn the wavefunction of datacited by 4
- 2024Tensor-Networks-based Learning of Probabilistic Cellular Automata Dynamicscited by 3
- 2021Infinitely Wide Tensor Networks as Gaussian Processcited by 2
- 2022Group-invariant tensor train networks for supervised learningcited by 1
- 2024Entangling Machine Learning with Quantum Tensor Networkscited by 0
- 2024Language Modeling Using Tensor Trains7 May 2024
- 2024Tensor-Networks-based Learning of Probabilistic Cellular Automata Dynamics17 Apr 2024
- 2024Entangling Machine Learning with Quantum Tensor Networks9 Jan 2024
- 2022Group-invariant tensor train networks for supervised learning30 Jun 2022
- 2021Tensor network to learn the wavefunction of data15 Nov 2021
- 2021Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework29 Jun 2021
- 2021Infinitely Wide Tensor Networks as Gaussian Process7 Jan 2021