@inproceedings{rabus-scherrer-2025-dialects,
title = "Dialects, Topic Models, and Border Effects: The {R}usyn Case",
author = "Rabus, Achim and
Scherrer, Yves",
editor = "Piskorski, Jakub and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Nakov, Preslav and
Yangarber, Roman and
Marcinczuk, Michal",
booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bsnlp-1.5/",
doi = "10.18653/v1/2025.bsnlp-1.5",
pages = "38--43",
ISBN = "978-1-959429-57-9",
abstract = "In this contribution, we present, discuss, and apply a data-driven approach for analyzing varieties of the Slavic minority language Carpathian Rusyn spoken in different countries in the Carpathian region. Using topic modeling, a method originally developed for text mining, we show that the Rusyn varieties are subject to border effects, i.e., vertical convergence and horizontal divergence, due to language contacts with their respective umbrella languages Polish, Slovak and Standard Ukrainian. Additionally, we show that the method is suitable for uncovering fieldworker isoglosses, i.e., different transcription principles in an otherwise homogeneous dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rabus-scherrer-2025-dialects">
<titleInfo>
<title>Dialects, Topic Models, and Border Effects: The Rusyn Case</title>
</titleInfo>
<name type="personal">
<namePart type="given">Achim</namePart>
<namePart type="family">Rabus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Marcinczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-1-959429-57-9</identifier>
</relatedItem>
<abstract>In this contribution, we present, discuss, and apply a data-driven approach for analyzing varieties of the Slavic minority language Carpathian Rusyn spoken in different countries in the Carpathian region. Using topic modeling, a method originally developed for text mining, we show that the Rusyn varieties are subject to border effects, i.e., vertical convergence and horizontal divergence, due to language contacts with their respective umbrella languages Polish, Slovak and Standard Ukrainian. Additionally, we show that the method is suitable for uncovering fieldworker isoglosses, i.e., different transcription principles in an otherwise homogeneous dataset.</abstract>
<identifier type="citekey">rabus-scherrer-2025-dialects</identifier>
<identifier type="doi">10.18653/v1/2025.bsnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2025.bsnlp-1.5/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>38</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialects, Topic Models, and Border Effects: The Rusyn Case
%A Rabus, Achim
%A Scherrer, Yves
%Y Piskorski, Jakub
%Y Přibáň, Pavel
%Y Nakov, Preslav
%Y Yangarber, Roman
%Y Marcinczuk, Michal
%S Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-57-9
%F rabus-scherrer-2025-dialects
%X In this contribution, we present, discuss, and apply a data-driven approach for analyzing varieties of the Slavic minority language Carpathian Rusyn spoken in different countries in the Carpathian region. Using topic modeling, a method originally developed for text mining, we show that the Rusyn varieties are subject to border effects, i.e., vertical convergence and horizontal divergence, due to language contacts with their respective umbrella languages Polish, Slovak and Standard Ukrainian. Additionally, we show that the method is suitable for uncovering fieldworker isoglosses, i.e., different transcription principles in an otherwise homogeneous dataset.
%R 10.18653/v1/2025.bsnlp-1.5
%U https://aclanthology.org/2025.bsnlp-1.5/
%U https://doi.org/10.18653/v1/2025.bsnlp-1.5
%P 38-43
Markdown (Informal)
[Dialects, Topic Models, and Border Effects: The Rusyn Case](https://aclanthology.org/2025.bsnlp-1.5/) (Rabus & Scherrer, BSNLP 2025)
ACL