@inproceedings{snee-etal-2025-unstable,
title = "Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists",
author = "Snee, David and
Ciucci, Luca and
Rubehn, Arne and
Dam, Kellen Parker Van and
List, Johann-Mattis",
editor = "Hahn, Michael and
Rani, Priya and
Kumar, Ritesh and
Shcherbakov, Andreas and
Sorokin, Alexey and
Serikov, Oleg and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sigtyp-1.3/",
doi = "10.18653/v1/2025.sigtyp-1.3",
pages = "16--28",
ISBN = "979-8-89176-281-7",
abstract = "Multilingual wordlists play a crucial role in comparative linguistics. While many studies have been carried out to test the power of computational methods for language subgrouping or divergence time estimation, few studies have put the data upon which these studies are based to a rigorous test. Here, we conduct a first experiment that tests the robustness of concept translation as an integral part of the compilation of multilingual wordlists. Investigating the variation in concept translations in independently compiled wordlists from 10 dataset pairs covering 9 different language families, we find that on average, only 83{\%} of all translations yield the same word form, while identical forms in terms of phonetic transcriptions can only be found in 23{\%} of all cases. Our findings can prove important when trying to assess the uncertainty of phylogenetic studies and the conclusions derived from them."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="snee-etal-2025-unstable">
<titleInfo>
<title>Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Snee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Ciucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arne</namePart>
<namePart type="family">Rubehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kellen</namePart>
<namePart type="given">Parker</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Dam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johann-Mattis</namePart>
<namePart type="family">List</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</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">979-8-89176-281-7</identifier>
</relatedItem>
<abstract>Multilingual wordlists play a crucial role in comparative linguistics. While many studies have been carried out to test the power of computational methods for language subgrouping or divergence time estimation, few studies have put the data upon which these studies are based to a rigorous test. Here, we conduct a first experiment that tests the robustness of concept translation as an integral part of the compilation of multilingual wordlists. Investigating the variation in concept translations in independently compiled wordlists from 10 dataset pairs covering 9 different language families, we find that on average, only 83% of all translations yield the same word form, while identical forms in terms of phonetic transcriptions can only be found in 23% of all cases. Our findings can prove important when trying to assess the uncertainty of phylogenetic studies and the conclusions derived from them.</abstract>
<identifier type="citekey">snee-etal-2025-unstable</identifier>
<identifier type="doi">10.18653/v1/2025.sigtyp-1.3</identifier>
<location>
<url>https://aclanthology.org/2025.sigtyp-1.3/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>16</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists
%A Snee, David
%A Ciucci, Luca
%A Rubehn, Arne
%A Dam, Kellen Parker Van
%A List, Johann-Mattis
%Y Hahn, Michael
%Y Rani, Priya
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Sorokin, Alexey
%Y Serikov, Oleg
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 7th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-281-7
%F snee-etal-2025-unstable
%X Multilingual wordlists play a crucial role in comparative linguistics. While many studies have been carried out to test the power of computational methods for language subgrouping or divergence time estimation, few studies have put the data upon which these studies are based to a rigorous test. Here, we conduct a first experiment that tests the robustness of concept translation as an integral part of the compilation of multilingual wordlists. Investigating the variation in concept translations in independently compiled wordlists from 10 dataset pairs covering 9 different language families, we find that on average, only 83% of all translations yield the same word form, while identical forms in terms of phonetic transcriptions can only be found in 23% of all cases. Our findings can prove important when trying to assess the uncertainty of phylogenetic studies and the conclusions derived from them.
%R 10.18653/v1/2025.sigtyp-1.3
%U https://aclanthology.org/2025.sigtyp-1.3/
%U https://doi.org/10.18653/v1/2025.sigtyp-1.3
%P 16-28
Markdown (Informal)
[Unstable Grounds for Beautiful Trees? Testing the Robustness of Concept Translations in the Compilation of Multilingual Wordlists](https://aclanthology.org/2025.sigtyp-1.3/) (Snee et al., SIGTYP 2025)
ACL