pith. sign in

arxiv: 1711.01416 · v1 · pith:3XH4HXWNnew · submitted 2017-11-04 · 💻 cs.CL · cond-mat.dis-nn· cs.LG· cs.NE· stat.ML

Language as a matrix product state

classification 💻 cs.CL cond-mat.dis-nncs.LGcs.NEstat.ML
keywords languageinvariantmatrixmeasureprobabilityproductstatetranslation
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.