@inproceedings{schuler-etal-2026-dialectal,
title = "Dialectal Filtering: Synthesizing {K}urdish Corpora for Low-Resource Varieties by Utilizing ``Noise'' in Large Textual Data",
author = "Schuler, Christian and
Ahmad, Raman and
W{\'a}ng, {\={A}}nr{\'a}n and
Gurgurov, Daniil and
Baumann, Timo and
Ostermann, Simon and
van Genabith, Josef",
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-1.116/",
doi = "10.63317/249h3r9tiw52",
pages = "1505--1519",
abstract = "This work introduces a dialect-aware text filtering framework to pre-process, clean, and enhance large text corpora, creating variety-specific sub-corpora for neglected language varieties. We apply our framework to Kurdish, a language with rich dialectal diversity, which presents significant challenges for Natural Language Processing due to its low-resource status and the noisy nature of available text corpora. Leveraging lexicographic features, we assign multi-language-labels to text instances and synthesize over 130 dialect specific corpora from large ``noisy'' data sets containing unlabeled mixtures of Kurdish varieties, representing to our knowledge the largest collection of dialect-specific Kurdish NLP resources to date. This work contributes to the creation of low-resource language technology foundations, especially dialect-specific NLP applications. Specifically, we advance research on Kurdish languages by providing insights into the linguistic relationships among Kurdish varieties."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schuler-etal-2026-dialectal">
<titleInfo>
<title>Dialectal Filtering: Synthesizing Kurdish Corpora for Low-Resource Varieties by Utilizing “Noise” in Large Textual Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Schuler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raman</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ānrán</namePart>
<namePart type="family">Wáng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Gurgurov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Baumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Ostermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</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>This work introduces a dialect-aware text filtering framework to pre-process, clean, and enhance large text corpora, creating variety-specific sub-corpora for neglected language varieties. We apply our framework to Kurdish, a language with rich dialectal diversity, which presents significant challenges for Natural Language Processing due to its low-resource status and the noisy nature of available text corpora. Leveraging lexicographic features, we assign multi-language-labels to text instances and synthesize over 130 dialect specific corpora from large “noisy” data sets containing unlabeled mixtures of Kurdish varieties, representing to our knowledge the largest collection of dialect-specific Kurdish NLP resources to date. This work contributes to the creation of low-resource language technology foundations, especially dialect-specific NLP applications. Specifically, we advance research on Kurdish languages by providing insights into the linguistic relationships among Kurdish varieties.</abstract>
<identifier type="citekey">schuler-etal-2026-dialectal</identifier>
<identifier type="doi">10.63317/249h3r9tiw52</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.116/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1505</start>
<end>1519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialectal Filtering: Synthesizing Kurdish Corpora for Low-Resource Varieties by Utilizing “Noise” in Large Textual Data
%A Schuler, Christian
%A Ahmad, Raman
%A Wáng, Ānrán
%A Gurgurov, Daniil
%A Baumann, Timo
%A Ostermann, Simon
%A van Genabith, Josef
%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 schuler-etal-2026-dialectal
%X This work introduces a dialect-aware text filtering framework to pre-process, clean, and enhance large text corpora, creating variety-specific sub-corpora for neglected language varieties. We apply our framework to Kurdish, a language with rich dialectal diversity, which presents significant challenges for Natural Language Processing due to its low-resource status and the noisy nature of available text corpora. Leveraging lexicographic features, we assign multi-language-labels to text instances and synthesize over 130 dialect specific corpora from large “noisy” data sets containing unlabeled mixtures of Kurdish varieties, representing to our knowledge the largest collection of dialect-specific Kurdish NLP resources to date. This work contributes to the creation of low-resource language technology foundations, especially dialect-specific NLP applications. Specifically, we advance research on Kurdish languages by providing insights into the linguistic relationships among Kurdish varieties.
%R 10.63317/249h3r9tiw52
%U https://aclanthology.org/2026.lrec-1.116/
%U https://doi.org/10.63317/249h3r9tiw52
%P 1505-1519
Markdown (Informal)
[Dialectal Filtering: Synthesizing Kurdish Corpora for Low-Resource Varieties by Utilizing "Noise" in Large Textual Data](https://aclanthology.org/2026.lrec-1.116/) (Schuler et al., LREC 2026)
ACL