@inproceedings{bompolas-etal-2026-cldf,
title = "A {CLDF}-Compliant Lexical Database for {M}odern {G}reek Dialects: Resource Design and Dialectometric Analysis",
author = "Bompolas, Stavros and
Chousou-Polydouri, Natalia and
Genitsaridi, Manuela and
Karatzanou, Danae and
Kostopoulos, Georgios and
Anagnostopoulou, Elena and
Melissaropoulou, Dimitra",
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-1.28/",
doi = "10.63317/33w8udv295cp",
pages = "287--299",
abstract = "This paper presents the first CLDF database that systematically documents lexical variation across 36 Modern Greek varieties (including Standard Modern Greek). The dataset aligns 14,378 lexical items over 345 concepts, links varieties to stable identifiers (Glottocodes), introduces a Greek-specific concept list, and maps meanings to standardized Concepticon concept sets, enabling interoperability and reproducible workflows. To assess whether the database preserves a meaningful dialectological signal, we conduct a dialectometric analysis by computing feature-sensitive string distances over IPA transcriptions and applying hierarchical clustering. The resulting similarity structure recovers major macro-divisions{---}most notably a broad Northern vs. Southern partition among Koine-descended mainland varieties{---}and isolates peripheral groups with distinct historical trajectories (e.g., Asia Minor, Italiot, Tsakonian). The database provides scalable infrastructure for quantitative dialectology, comparative Greek linguistics, and dialect-aware language technology."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bompolas-etal-2026-cldf">
<titleInfo>
<title>A CLDF-Compliant Lexical Database for Modern Greek Dialects: Resource Design and Dialectometric Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stavros</namePart>
<namePart type="family">Bompolas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Chousou-Polydouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuela</namePart>
<namePart type="family">Genitsaridi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danae</namePart>
<namePart type="family">Karatzanou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Kostopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Anagnostopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Melissaropoulou</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 the first CLDF database that systematically documents lexical variation across 36 Modern Greek varieties (including Standard Modern Greek). The dataset aligns 14,378 lexical items over 345 concepts, links varieties to stable identifiers (Glottocodes), introduces a Greek-specific concept list, and maps meanings to standardized Concepticon concept sets, enabling interoperability and reproducible workflows. To assess whether the database preserves a meaningful dialectological signal, we conduct a dialectometric analysis by computing feature-sensitive string distances over IPA transcriptions and applying hierarchical clustering. The resulting similarity structure recovers major macro-divisions—most notably a broad Northern vs. Southern partition among Koine-descended mainland varieties—and isolates peripheral groups with distinct historical trajectories (e.g., Asia Minor, Italiot, Tsakonian). The database provides scalable infrastructure for quantitative dialectology, comparative Greek linguistics, and dialect-aware language technology.</abstract>
<identifier type="citekey">bompolas-etal-2026-cldf</identifier>
<identifier type="doi">10.63317/33w8udv295cp</identifier>
<location>
<url>https://aclanthology.org/2026.dialres-1.28/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>287</start>
<end>299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A CLDF-Compliant Lexical Database for Modern Greek Dialects: Resource Design and Dialectometric Analysis
%A Bompolas, Stavros
%A Chousou-Polydouri, Natalia
%A Genitsaridi, Manuela
%A Karatzanou, Danae
%A Kostopoulos, Georgios
%A Anagnostopoulou, Elena
%A Melissaropoulou, Dimitra
%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 bompolas-etal-2026-cldf
%X This paper presents the first CLDF database that systematically documents lexical variation across 36 Modern Greek varieties (including Standard Modern Greek). The dataset aligns 14,378 lexical items over 345 concepts, links varieties to stable identifiers (Glottocodes), introduces a Greek-specific concept list, and maps meanings to standardized Concepticon concept sets, enabling interoperability and reproducible workflows. To assess whether the database preserves a meaningful dialectological signal, we conduct a dialectometric analysis by computing feature-sensitive string distances over IPA transcriptions and applying hierarchical clustering. The resulting similarity structure recovers major macro-divisions—most notably a broad Northern vs. Southern partition among Koine-descended mainland varieties—and isolates peripheral groups with distinct historical trajectories (e.g., Asia Minor, Italiot, Tsakonian). The database provides scalable infrastructure for quantitative dialectology, comparative Greek linguistics, and dialect-aware language technology.
%R 10.63317/33w8udv295cp
%U https://aclanthology.org/2026.dialres-1.28/
%U https://doi.org/10.63317/33w8udv295cp
%P 287-299
Markdown (Informal)
[A CLDF-Compliant Lexical Database for Modern Greek Dialects: Resource Design and Dialectometric Analysis](https://aclanthology.org/2026.dialres-1.28/) (Bompolas et al., DialRes 2026)
ACL