EUVIMEDEUVIMED entdecken
Crossref

Gaussianity and typicality in matrix distributional semantics

Sanjaye Ramgoolam, Mehrnoosh Sadrzadeh, Lewis Sword

Annales de l’Institut Henri Poincaré D, Combinatorics, Physics and their Interactions · 2022

DOI: 10.4171/aihpd/112 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annales de l’Institut Henri Poincaré D, Combinatorics, Physics and their Interactions, 2022. Verfasst von Sanjaye Ramgoolam und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Constructions in type-driven compositional distributional semantics associate large collections of matrices of size D to linguistic corpora. We develop the proposal of analysing the statistical characteristics of this data in the framework of permutation invariant matrix models. The observables in this framework are permutation invariant polynomial functions of the matrix entries, which correspond to directed graphs. Using the general 13-parameter permutation invariant Gaussian matrix models recently solved, we find, using a dataset of matrices constructed via standard techniques in distributional semantics, that the expectation values of a large class of cubic and quartic observables show high Gaussianity at levels between 90 to 99 percent. Beyond expectation values, which are averages over words, the dataset allows the computation of standard deviations for each observable, which can be viewed as a measure of typicality for each observable. There is a wide range of magnitudes in the measures of typicality. The permutation invariant matrix models, considered as functions of random couplings, give a very good prediction of the magnitude of the typicality for different observables. We find evidence that observables with similar matrix model characteristics of Gaussianity and typicality also have high degrees of correlation between the ranked lists of words associated to these observables.

Zitieren

APA

Ramgoolam, S., Sadrzadeh, M., & Sword, L. (2022). Gaussianity and typicality in matrix distributional semantics. Annales de l’Institut Henri Poincaré D, Combinatorics, Physics and their Interactions. https://doi.org/10.4171/aihpd/112

Vancouver

Ramgoolam S, Sadrzadeh M, Sword L. Gaussianity and typicality in matrix distributional semantics. Annales de l’Institut Henri Poincaré D, Combinatorics, Physics and their Interactions. 2022. doi:10.4171/aihpd/112

BibTeX
@article{Ramgoolam2022,
  author = {Ramgoolam, Sanjaye and Sadrzadeh, Mehrnoosh and Sword, Lewis},
  title = {Gaussianity and typicality in matrix distributional semantics},
  journal = {Annales de l’Institut Henri Poincaré D, Combinatorics, Physics and their Interactions},
  year = {2022},
  doi = {10.4171/aihpd/112}
}
Kostenlos starten →