Permutation invariant matrix statistics and computational language tasks

02/14/2022
by   Manuel Accettulli Huber, et al.
5

The Linguistic Matrix Theory programme introduced by Kartsaklis, Ramgoolam and Sadrzadeh is an approach to the statistics of matrices that are generated in type-driven distributional semantics, based on permutation invariant polynomial functions which are regarded as the key observables encoding the significant statistics. In this paper we generalize the previous results on the approximate Gaussianity of matrix distributions arising from compositional distributional semantics. We also introduce a geometry of observable vectors for words, defined by exploiting the graph-theoretic basis for the permutation invariants and the statistical characteristics of the ensemble of matrices associated with the words. We describe successful applications of this unified framework to a number of tasks in computational linguistics, associated with the distinctions between synonyms, antonyms, hypernyms and hyponyms.

READ FULL TEXT

page 14

page 20

page 21

page 23

research
12/19/2019

Gaussianity and typicality in matrix distributional semantics

Constructions in type-driven compositional distributional semantics asso...
research
03/28/2017

Linguistic Matrix Theory

Recent research in computational linguistics has developed algorithms wh...
research
09/20/2018

Permutation Invariant Gaussian Matrix Models

Permutation invariant Gaussian matrix models were recently developed for...
research
07/03/2023

Learning permutation symmetries with gips in R

The study of hidden structures in data presents challenges in modern sta...
research
04/27/2020

A general method for finding the compositional inverses of permutations from the AGW criterion

Permutation polynomials and their compositional inverses have wide appli...
research
08/26/2017

Mahonian STAT on rearrangement class of words

In 2000, Babson and Steingrímsson generalized the notion of permutation ...
research
11/04/2017

Language as a matrix product state

We propose a statistical model for natural language that begins by consi...

Please sign up or login with your details

Forgot password? Click here to reset