Language as a matrix product state
Computation and Language
2017-11-07 v1 Disordered Systems and Neural Networks
Machine Learning
Neural and Evolutionary Computing
Machine Learning
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.
Keywords
Cite
@article{arxiv.1711.01416,
title = {Language as a matrix product state},
author = {Vasily Pestun and John Terilla and Yiannis Vlassopoulos},
journal= {arXiv preprint arXiv:1711.01416},
year = {2017}
}
Comments
10 pages