Linguistic matrix theory

DOI10.4171/AIHPD/75MaRDI QIDQ2327722zbMATH OpenFDO

Authors Dimitrios Kartsaklis, Sanjaye Ramgoolam, Mehrnoosh Sadrzadeh

Publication date 15 October 2019

Published in Annales de l'Institut Henri Poincaré D. Combinatorics, Physics and their Interactions (AIHPD) (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1703.10252

zbMATH Keywords

distributional semantics matrix models natural language processing permutation invariant distributions random maps random matrix theory tensor models topological gravity

Mathematics Subject Classification ID

Random matrices (algebraic aspects) (15B52) Linguistics (91F20)

Abstract: Recent research in computational linguistics has developed algorithms which associate matrices with adjectives and verbs, based on the distribution of words in a corpus of text. These matrices are linear operators on a vector space of context words. They are used to construct the meaning of composite expressions from that of the elementary constituents, forming part of a compositional distributional approach to semantics. We propose a Matrix Theory approach to this data, based on permutation symmetry along with Gaussian weights and their perturbations. A simple Gaussian model is tested against word matrices created from a large corpus of text. We characterize the cubic and quartic departures from the model, which we propose, alongside the Gaussian parameters, as signatures for comparison of linguistic corpora. We propose that perturbed Gaussian models with permutation symmetry provide a promising framework for characterizing the nature of universality in the statistical properties of word matrices. The matrix theory framework developed here exploits the view of statistics as zero dimensional perturbative quantum field theory. It perceives language as a physical system realizing a universality class of matrix statistics characterized by permutation symmetry.

Review text

Summary: Recent research in computational linguistics has developed algorithms which associate matrices with adjectives and verbs, based on the distribution of words in a corpus of text. These matrices are linear operators on a vector space of context words. They are used to construct meaning representations for composite expressions from that of the elementary constituents, forming part of a compositional distributional approach to semantics. We propose a matrix theory approach to this data, based on permutation symmetry along with Gaussian weights and their perturbations. A simple Gaussian model is tested against word matrices created from a large corpus of text. We characterize the cubic and quartic departures from the model, which we propose, alongside the Gaussian parameters, as signatures for comparison of linguistic corpora. We propose that perturbed Gaussian models with permutation symmetry provide a promising framework for characterizing the nature of universality in the statistical properties of word matrices. The matrix theory framework developed here exploits the view of statistics as zero dimensional perturbative quantum field theory. It perceives language as a physical system realizing a universality class of matrix statistics characterized by permutation symmetry.

Recommendations

Cites work

Cited in

(10)

This page was built for publication: Linguistic matrix theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2327722)