The EMS Publishing House is now EMS Press and has its new home at ems.press.

Please find all EMS Press journals and articles on the new platform.

Annales de l’Institut Henri Poincaré D


Full-Text PDF (577 KB) | Metadata | Table of Contents | AIHPD summary
Volume 6, Issue 3, 2019, pp. 385–426
DOI: 10.4171/AIHPD/75

Published online: 2019-05-07

Linguistic matrix theory

Dimitrios Kartsaklis[1], Sanjaye Ramgoolam[2] and Mehrnoosh Sadrzadeh[3]

(1) Queen Mary University of London, UK
(2) Queen Mary University of London, UK
(3) Queen Mary University of London, UK

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.

Keywords: Distributional semantics, matrix models, natural language processing, permutation invariant distributions, random maps, random matrix theory, tensor models, topological gravity

Kartsaklis Dimitrios, Ramgoolam Sanjaye, Sadrzadeh Mehrnoosh: Linguistic matrix theory. Ann. Inst. Henri Poincaré Comb. Phys. Interact. 6 (2019), 385-426. doi: 10.4171/AIHPD/75