@inproceedings{karakas-2026-transfer,
title = "Transfer Learning for an Endangered {S}lavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects",
author = "Karakas, Sercan",
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-1.34/",
doi = "10.63317/2mrmccuuhkgf",
pages = "345--354",
abstract = {This paper presents new resources and baselines for Dependency Parsing in Pomak, an endangered Eastern South Slavic language with substantial dialectal variation and no widely adopted standard. We focus on the variety spoken in Turkey (Uzunk{\"o}pr{\"u}) and ask how well a dependency parser trained on the existing Pomak Universal Dependencies treebank, which was built primarily from the variety that is spoken in Greece, transfers across dialects. We run two experimental phases. First, we train a parser on the Greek-variety UD data and evaluate zero-shot transfer to Turkish-variety Pomak, quantifying the impact of phonological and morphosyntactic differences. Second, we introduce a new manually annotated Turkish-variety Pomak corpus of 650 sentences and show that, despite its small size, targeted fine-tuning substantially improves accuracy; performance is further boosted by cross-variety transfer learning that combines the two dialects.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karakas-2026-transfer">
<titleInfo>
<title>Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sercan</namePart>
<namePart type="family">Karakas</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>This paper presents new resources and baselines for Dependency Parsing in Pomak, an endangered Eastern South Slavic language with substantial dialectal variation and no widely adopted standard. We focus on the variety spoken in Turkey (Uzunköprü) and ask how well a dependency parser trained on the existing Pomak Universal Dependencies treebank, which was built primarily from the variety that is spoken in Greece, transfers across dialects. We run two experimental phases. First, we train a parser on the Greek-variety UD data and evaluate zero-shot transfer to Turkish-variety Pomak, quantifying the impact of phonological and morphosyntactic differences. Second, we introduce a new manually annotated Turkish-variety Pomak corpus of 650 sentences and show that, despite its small size, targeted fine-tuning substantially improves accuracy; performance is further boosted by cross-variety transfer learning that combines the two dialects.</abstract>
<identifier type="citekey">karakas-2026-transfer</identifier>
<identifier type="doi">10.63317/2mrmccuuhkgf</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.34/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>345</start>
<end>354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects
%A Karakas, Sercan
%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 karakas-2026-transfer
%X This paper presents new resources and baselines for Dependency Parsing in Pomak, an endangered Eastern South Slavic language with substantial dialectal variation and no widely adopted standard. We focus on the variety spoken in Turkey (Uzunköprü) and ask how well a dependency parser trained on the existing Pomak Universal Dependencies treebank, which was built primarily from the variety that is spoken in Greece, transfers across dialects. We run two experimental phases. First, we train a parser on the Greek-variety UD data and evaluate zero-shot transfer to Turkish-variety Pomak, quantifying the impact of phonological and morphosyntactic differences. Second, we introduce a new manually annotated Turkish-variety Pomak corpus of 650 sentences and show that, despite its small size, targeted fine-tuning substantially improves accuracy; performance is further boosted by cross-variety transfer learning that combines the two dialects.
%R 10.63317/2mrmccuuhkgf
%U https://aclanthology.org/2026.dialres-1.34/
%U https://doi.org/10.63317/2mrmccuuhkgf
%P 345-354
Markdown (Informal)
[Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects](https://aclanthology.org/2026.dialres-1.34/) (Karakas, DialRes 2026)
ACL