@inproceedings{nedey-etal-2026-forumoccitania,
title = "{F}orum{O}ccitania: A Corpus of User-Generated Content for Multiple {O}ccitan Varieties",
author = "N{\'e}dey, Oriane and
Jan{\`e}s, Juliette and
Bawden, Rachel and
Cl{\'e}rice, Thibault and
Sagot, Beno{\^i}t",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.252/",
doi = "10.63317/3h3c8smpj9p2",
pages = "3220--3233",
abstract = "We introduce ForumOccitania, a new Occitan corpus of posts from an online forum, covering a range of topics and dialects. While some existing datasets for this low-resource language include labels of varieties within the dialect continuum, we go one step further by providing metadata pertaining to sociolinguistic factors of language variation (dialect, geographical location, age, proficiency), extracted from self-declared user profiles. We carry out statistical and qualitative analyses, as well as preliminary experiments on unsupervised dialect identification. Our results show that (i) most of the contents is written in Occitan, with the classical spelling conventions, and by young speakers, (ii) posts display a strong presence of dialectal features from four major Occitan varieties (Lemosin, Lengadocian, Gascon, Proven{\c{c}}au), and (iii) a simple topic modelling approach introduced by Kuparinen and Scherrer (2024) effectively detects salient features of these four varieties, but also reveals finer-grained diatopical variation tendencies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nedey-etal-2026-forumoccitania">
<titleInfo>
<title>ForumOccitania: A Corpus of User-Generated Content for Multiple Occitan Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oriane</namePart>
<namePart type="family">Nédey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliette</namePart>
<namePart type="family">Janès</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</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>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce ForumOccitania, a new Occitan corpus of posts from an online forum, covering a range of topics and dialects. While some existing datasets for this low-resource language include labels of varieties within the dialect continuum, we go one step further by providing metadata pertaining to sociolinguistic factors of language variation (dialect, geographical location, age, proficiency), extracted from self-declared user profiles. We carry out statistical and qualitative analyses, as well as preliminary experiments on unsupervised dialect identification. Our results show that (i) most of the contents is written in Occitan, with the classical spelling conventions, and by young speakers, (ii) posts display a strong presence of dialectal features from four major Occitan varieties (Lemosin, Lengadocian, Gascon, Provençau), and (iii) a simple topic modelling approach introduced by Kuparinen and Scherrer (2024) effectively detects salient features of these four varieties, but also reveals finer-grained diatopical variation tendencies.</abstract>
<identifier type="citekey">nedey-etal-2026-forumoccitania</identifier>
<identifier type="doi">10.63317/3h3c8smpj9p2</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.252/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3220</start>
<end>3233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ForumOccitania: A Corpus of User-Generated Content for Multiple Occitan Varieties
%A Nédey, Oriane
%A Janès, Juliette
%A Bawden, Rachel
%A Clérice, Thibault
%A Sagot, Benoît
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F nedey-etal-2026-forumoccitania
%X We introduce ForumOccitania, a new Occitan corpus of posts from an online forum, covering a range of topics and dialects. While some existing datasets for this low-resource language include labels of varieties within the dialect continuum, we go one step further by providing metadata pertaining to sociolinguistic factors of language variation (dialect, geographical location, age, proficiency), extracted from self-declared user profiles. We carry out statistical and qualitative analyses, as well as preliminary experiments on unsupervised dialect identification. Our results show that (i) most of the contents is written in Occitan, with the classical spelling conventions, and by young speakers, (ii) posts display a strong presence of dialectal features from four major Occitan varieties (Lemosin, Lengadocian, Gascon, Provençau), and (iii) a simple topic modelling approach introduced by Kuparinen and Scherrer (2024) effectively detects salient features of these four varieties, but also reveals finer-grained diatopical variation tendencies.
%R 10.63317/3h3c8smpj9p2
%U https://aclanthology.org/2026.lrec-1.252/
%U https://doi.org/10.63317/3h3c8smpj9p2
%P 3220-3233
Markdown (Informal)
[ForumOccitania: A Corpus of User-Generated Content for Multiple Occitan Varieties](https://aclanthology.org/2026.lrec-1.252/) (Nédey et al., LREC 2026)
ACL