@inproceedings{berikashvili-skopeteas-2026-pontic,
title = "{P}ontic {G}reek in the {C}aucasus: an online corpus",
author = "Berikashvili, Svetlana and
Skopeteas, Stavros",
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-1.23/",
doi = "10.63317/5h5zzmh3vmmh",
pages = "230--237",
abstract = "This paper presents a multi-media corpus of Pontic Greek as spoken by Pontic Greek speakers in the Caucasus (Georgia). The corpus covers three major stages reflecting different sociolinguistic settings: (a) Ponitc Greek in small rural communities in Georgia (original settlements); (b) internal migration to urban centers (within Georgia), (c) external migration (to Greece). The dataset comprises 373 audio recordings (total duration 7h 26m; total word count: 43.073). The open-access resource includes audio files (wav) and annotations (xml). Annotations provide orthographical transcription, morphemic transcription and morpheme-by-morpheme and sentence-by-sentence translations in English (Toolbox); transcriptions are time-aligned with the audio files (ELAN). This collection is intended to linguists working on dialectology and language contact, as well as people with broader interests about the history and practices of this community. Pontic Greek in the Caucasus offers a unique opportunity to investigate contact between Greek and another Indo-European language (Russian) as well as two Non-Indo-European languages (Georgian, Turkish)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berikashvili-skopeteas-2026-pontic">
<titleInfo>
<title>Pontic Greek in the Caucasus: an online corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Berikashvili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stavros</namePart>
<namePart type="family">Skopeteas</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 a multi-media corpus of Pontic Greek as spoken by Pontic Greek speakers in the Caucasus (Georgia). The corpus covers three major stages reflecting different sociolinguistic settings: (a) Ponitc Greek in small rural communities in Georgia (original settlements); (b) internal migration to urban centers (within Georgia), (c) external migration (to Greece). The dataset comprises 373 audio recordings (total duration 7h 26m; total word count: 43.073). The open-access resource includes audio files (wav) and annotations (xml). Annotations provide orthographical transcription, morphemic transcription and morpheme-by-morpheme and sentence-by-sentence translations in English (Toolbox); transcriptions are time-aligned with the audio files (ELAN). This collection is intended to linguists working on dialectology and language contact, as well as people with broader interests about the history and practices of this community. Pontic Greek in the Caucasus offers a unique opportunity to investigate contact between Greek and another Indo-European language (Russian) as well as two Non-Indo-European languages (Georgian, Turkish).</abstract>
<identifier type="citekey">berikashvili-skopeteas-2026-pontic</identifier>
<identifier type="doi">10.63317/5h5zzmh3vmmh</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.23/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>230</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pontic Greek in the Caucasus: an online corpus
%A Berikashvili, Svetlana
%A Skopeteas, Stavros
%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 berikashvili-skopeteas-2026-pontic
%X This paper presents a multi-media corpus of Pontic Greek as spoken by Pontic Greek speakers in the Caucasus (Georgia). The corpus covers three major stages reflecting different sociolinguistic settings: (a) Ponitc Greek in small rural communities in Georgia (original settlements); (b) internal migration to urban centers (within Georgia), (c) external migration (to Greece). The dataset comprises 373 audio recordings (total duration 7h 26m; total word count: 43.073). The open-access resource includes audio files (wav) and annotations (xml). Annotations provide orthographical transcription, morphemic transcription and morpheme-by-morpheme and sentence-by-sentence translations in English (Toolbox); transcriptions are time-aligned with the audio files (ELAN). This collection is intended to linguists working on dialectology and language contact, as well as people with broader interests about the history and practices of this community. Pontic Greek in the Caucasus offers a unique opportunity to investigate contact between Greek and another Indo-European language (Russian) as well as two Non-Indo-European languages (Georgian, Turkish).
%R 10.63317/5h5zzmh3vmmh
%U https://aclanthology.org/2026.dialres-1.23/
%U https://doi.org/10.63317/5h5zzmh3vmmh
%P 230-237
Markdown (Informal)
[Pontic Greek in the Caucasus: an online corpus](https://aclanthology.org/2026.dialres-1.23/) (Berikashvili & Skopeteas, DialRes 2026)
ACL
- Svetlana Berikashvili and Stavros Skopeteas. 2026. Pontic Greek in the Caucasus: an online corpus. In Proceedings of the First Workshop on Dialects in NLP — A Resource Perspective, pages 230–237, Palma de Mallorca. Association for Computational Linguistics.