@inproceedings{frund-ahmadi-2026-dialectal,
title = "A Dialectal Corpus for {U}krainian: Collection, Classification, and Standardization",
author = "Frund, Yuliia and
Ahmadi, Sina",
editor = "Anastasopoulos, Antonis and
Markantonatou, Stella and
Ralli, Angela and
Zampieri, Marcos and
Bompolas, Stavros and
Stamou, Vivian",
booktitle = "Proceedings of the First Workshop on Dialects in {NLP} {---} A Resource Perspective",
month = may,
year = "2026",
address = "Palma de Mallorca",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dialres-1.14/",
doi = "10.63317/4mkaru7y2op5",
pages = "135--143",
abstract = "Ukrainian dialects remain largely excluded from the digital linguistic landscape despite their active everyday use. We present a regional dialect corpus covering 18 administrative regions of Ukraine, compiled from digitized fieldwork collections and an online dialect atlas. The corpus comprises over 284,000 tokens of dialect text, annotated by region and partially accompanied by manually standardized translations. Using these resources, we investigate language identification and dialect-to-standard standardization. Baseline language identification yields an F-score of 0.75, rising to 0.99 with dialect-inclusive training. Dialect classification reaches 0.58, with confusion patterns reflecting known regional boundaries. For standardization, the best-performing LLM achieves a COMET score of 0.80, though BLEU scores remain low (0.21{--}0.23) across all models. We release the corpus, labelled datasets, model outputs, and reference translations to support future work on inclusive language technologies for non-standard varieties."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frund-ahmadi-2026-dialectal">
<titleInfo>
<title>A Dialectal Corpus for Ukrainian: Collection, Classification, and Standardization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuliia</namePart>
<namePart type="family">Frund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</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 First Workshop on Dialects in NLP — A Resource Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Ralli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stavros</namePart>
<namePart type="family">Bompolas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Stamou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ukrainian dialects remain largely excluded from the digital linguistic landscape despite their active everyday use. We present a regional dialect corpus covering 18 administrative regions of Ukraine, compiled from digitized fieldwork collections and an online dialect atlas. The corpus comprises over 284,000 tokens of dialect text, annotated by region and partially accompanied by manually standardized translations. Using these resources, we investigate language identification and dialect-to-standard standardization. Baseline language identification yields an F-score of 0.75, rising to 0.99 with dialect-inclusive training. Dialect classification reaches 0.58, with confusion patterns reflecting known regional boundaries. For standardization, the best-performing LLM achieves a COMET score of 0.80, though BLEU scores remain low (0.21–0.23) across all models. We release the corpus, labelled datasets, model outputs, and reference translations to support future work on inclusive language technologies for non-standard varieties.</abstract>
<identifier type="citekey">frund-ahmadi-2026-dialectal</identifier>
<identifier type="doi">10.63317/4mkaru7y2op5</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>135</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dialectal Corpus for Ukrainian: Collection, Classification, and Standardization
%A Frund, Yuliia
%A Ahmadi, Sina
%Y Anastasopoulos, Antonis
%Y Markantonatou, Stella
%Y Ralli, Angela
%Y Zampieri, Marcos
%Y Bompolas, Stavros
%Y Stamou, Vivian
%S Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca
%F frund-ahmadi-2026-dialectal
%X Ukrainian dialects remain largely excluded from the digital linguistic landscape despite their active everyday use. We present a regional dialect corpus covering 18 administrative regions of Ukraine, compiled from digitized fieldwork collections and an online dialect atlas. The corpus comprises over 284,000 tokens of dialect text, annotated by region and partially accompanied by manually standardized translations. Using these resources, we investigate language identification and dialect-to-standard standardization. Baseline language identification yields an F-score of 0.75, rising to 0.99 with dialect-inclusive training. Dialect classification reaches 0.58, with confusion patterns reflecting known regional boundaries. For standardization, the best-performing LLM achieves a COMET score of 0.80, though BLEU scores remain low (0.21–0.23) across all models. We release the corpus, labelled datasets, model outputs, and reference translations to support future work on inclusive language technologies for non-standard varieties.
%R 10.63317/4mkaru7y2op5
%U https://aclanthology.org/2026.dialres-1.14/
%U https://doi.org/10.63317/4mkaru7y2op5
%P 135-143
Markdown (Informal)
[A Dialectal Corpus for Ukrainian: Collection, Classification, and Standardization](https://aclanthology.org/2026.dialres-1.14/) (Frund & Ahmadi, DialRes 2026)
ACL