@inproceedings{dent-etal-2026-model,
title = "How Should We Model the Probability of a Language?",
author = "Dent, Rasul and
Ortiz Suarez, Pedro and
Cl{\'e}rice, Thibault and
Sagot, Beno{\^i}t",
booktitle = "Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.vardial-1.18/",
pages = "223--233",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dent-etal-2026-model">
<titleInfo>
<title>How Should We Model the Probability of a Language?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rasul</namePart>
<namePart type="family">Dent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ortiz Suarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Clérice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">dent-etal-2026-model</identifier>
<location>
<url>https://aclanthology.org/2026.vardial-1.18/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>223</start>
<end>233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Should We Model the Probability of a Language?
%A Dent, Rasul
%A Ortiz Suarez, Pedro
%A Clérice, Thibault
%A Sagot, Benoît
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F dent-etal-2026-model
%X 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.
%U https://aclanthology.org/2026.vardial-1.18/
%P 223-233
Markdown (Informal)
[How Should We Model the Probability of a Language?](https://aclanthology.org/2026.vardial-1.18/) (Dent et al., VarDial 2026)
ACL
- Rasul Dent, Pedro Ortiz Suarez, Thibault Clérice, and Benoît Sagot. 2026. How Should We Model the Probability of a Language?. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 223–233, Rabat, Morocco. Association for Computational Linguistics.