2000 character limit reached
Language as a matrix product state
Published 4 Nov 2017 in cs.CL, cond-mat.dis-nn, cs.LG, cs.NE, and stat.ML | (1711.01416v1)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.