Guardado en:
Detalles Bibliográficos
Autor principal: Ding, Chenchen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.00271
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914662481657856
author Ding, Chenchen
author_facet Ding, Chenchen
contents $f \propto r^{-α} \cdot (r+γ)^{-β}$ has been empirically shown more precise than a naïve power law $f\propto r^{-α}$ to model the rank-frequency ($r$-$f$) relation of words in natural languages. This work shows that the only crucial parameter in the formulation is $γ$, which depicts the resistance to vocabulary growth on a corpus. A method of parameter estimation by searching an optimal $γ$ is proposed, where a ``zeroth word'' is introduced technically for the calculation. The formulation and parameters are further discussed with several case studies.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00271
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Crucial Parameter for Rank-Frequency Relation in Natural Languages
Ding, Chenchen
Computation and Language
$f \propto r^{-α} \cdot (r+γ)^{-β}$ has been empirically shown more precise than a naïve power law $f\propto r^{-α}$ to model the rank-frequency ($r$-$f$) relation of words in natural languages. This work shows that the only crucial parameter in the formulation is $γ$, which depicts the resistance to vocabulary growth on a corpus. A method of parameter estimation by searching an optimal $γ$ is proposed, where a ``zeroth word'' is introduced technically for the calculation. The formulation and parameters are further discussed with several case studies.
title A Crucial Parameter for Rank-Frequency Relation in Natural Languages
topic Computation and Language
url https://arxiv.org/abs/2402.00271