Language as a matrix product state

Abstract

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.

10 pages

References in corpus (1)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Cited by in corpus (6)

• Tensor network to learn the wavefunction of data
• Language Modeling with Reduced Densities
• Tensor Networks for Probabilistic Sequence Modeling
• Infinitely Wide Tensor Networks as Gaussian Process
• Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework
• At the Interface of Algebra and Statistics