How Should We Model the Probability of a Language?

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dent, Rasul, Suarez, Pedro Ortiz, Clérice, Thibault, Sagot, Benoît
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911435180736512
author Dent, Rasul
Suarez, Pedro Ortiz
Clérice, Thibault
Sagot, Benoît
author_facet Dent, Rasul
Suarez, Pedro Ortiz
Clérice, Thibault
Sagot, Benoît
contents Of the over 7,000 languages spoken in the world, commercial language identification (LID) systems only reliably identify a few hundred in written form. Research-grade systems extend this coverage under certain circumstances, but for most languages coverage remains patchy or nonexistent. This position paper argues that this situation is largely self-imposed. In particular, it arises from a persistent framing of LID as decontextualized text classification, which obscures the central role of prior probability estimation and is reinforced by institutional incentives that favor global, fixed-prior models. We argue that improving coverage for tail languages requires rethinking LID as a routing problem and developing principled ways to incorporate environmental cues that make languages locally plausible.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08951
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How Should We Model the Probability of a Language?
Dent, Rasul
Suarez, Pedro Ortiz
Clérice, Thibault
Sagot, Benoît
Computation and Language
Of the over 7,000 languages spoken in the world, commercial language identification (LID) systems only reliably identify a few hundred in written form. Research-grade systems extend this coverage under certain circumstances, but for most languages coverage remains patchy or nonexistent. This position paper argues that this situation is largely self-imposed. In particular, it arises from a persistent framing of LID as decontextualized text classification, which obscures the central role of prior probability estimation and is reinforced by institutional incentives that favor global, fixed-prior models. We argue that improving coverage for tail languages requires rethinking LID as a routing problem and developing principled ways to incorporate environmental cues that make languages locally plausible.
title How Should We Model the Probability of a Language?
topic Computation and Language
url https://arxiv.org/abs/2602.08951