@inproceedings{rapacz-smywinski-pohl-2026-targum,
title = "Targum {---} a Multilingual {N}ew {T}estament Translation Corpus",
author = "Rapacz, Maciej and
Smywi{\'n}ski-Pohl, Aleksander",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.564/",
doi = "10.63317/2yiotxcyovir",
pages = "7092--7105",
abstract = "Many European languages possess rich biblical translation histories, yet existing corpora {---} in prioritizing linguistic breadth {---} often fail to capture this depth. To address this gap, we introduce a multilingual corpus of 651 New Testament translations, of which 334 are unique, spanning five languages with 2.4{--}5.0{\texttimes} more translations per language than any prior corpus: English (194 unique versions from 390 total), French (41 from 78), Italian (17 from 33), Polish (29 from 48), and Spanish (53 from 102). Aggregated from 12 online biblical libraries and one preexisting corpus, each translation is annotated with metadata that maps the text to a standardized identifier for the work, its specific edition, and its year of revision. This canonicalization allows researchers to define ``uniqueness'' for their own needs: they can perform micro-level analyses on translation families, such as the KJV lineage, or conduct macro-level studies by deduplicating closely related texts. By providing the first multilingual resource with sufficient depth per language for flexible, multilevel analysis, the corpus fills a gap in the quantitative study of translation history."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rapacz-smywinski-pohl-2026-targum">
<titleInfo>
<title>Targum — a Multilingual New Testament Translation Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Rapacz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Smywiński-Pohl</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many European languages possess rich biblical translation histories, yet existing corpora — in prioritizing linguistic breadth — often fail to capture this depth. To address this gap, we introduce a multilingual corpus of 651 New Testament translations, of which 334 are unique, spanning five languages with 2.4–5.0× more translations per language than any prior corpus: English (194 unique versions from 390 total), French (41 from 78), Italian (17 from 33), Polish (29 from 48), and Spanish (53 from 102). Aggregated from 12 online biblical libraries and one preexisting corpus, each translation is annotated with metadata that maps the text to a standardized identifier for the work, its specific edition, and its year of revision. This canonicalization allows researchers to define “uniqueness” for their own needs: they can perform micro-level analyses on translation families, such as the KJV lineage, or conduct macro-level studies by deduplicating closely related texts. By providing the first multilingual resource with sufficient depth per language for flexible, multilevel analysis, the corpus fills a gap in the quantitative study of translation history.</abstract>
<identifier type="citekey">rapacz-smywinski-pohl-2026-targum</identifier>
<identifier type="doi">10.63317/2yiotxcyovir</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.564/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7092</start>
<end>7105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Targum — a Multilingual New Testament Translation Corpus
%A Rapacz, Maciej
%A Smywiński-Pohl, Aleksander
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F rapacz-smywinski-pohl-2026-targum
%X Many European languages possess rich biblical translation histories, yet existing corpora — in prioritizing linguistic breadth — often fail to capture this depth. To address this gap, we introduce a multilingual corpus of 651 New Testament translations, of which 334 are unique, spanning five languages with 2.4–5.0× more translations per language than any prior corpus: English (194 unique versions from 390 total), French (41 from 78), Italian (17 from 33), Polish (29 from 48), and Spanish (53 from 102). Aggregated from 12 online biblical libraries and one preexisting corpus, each translation is annotated with metadata that maps the text to a standardized identifier for the work, its specific edition, and its year of revision. This canonicalization allows researchers to define “uniqueness” for their own needs: they can perform micro-level analyses on translation families, such as the KJV lineage, or conduct macro-level studies by deduplicating closely related texts. By providing the first multilingual resource with sufficient depth per language for flexible, multilevel analysis, the corpus fills a gap in the quantitative study of translation history.
%R 10.63317/2yiotxcyovir
%U https://aclanthology.org/2026.lrec-1.564/
%U https://doi.org/10.63317/2yiotxcyovir
%P 7092-7105
Markdown (Informal)
[Targum — a Multilingual New Testament Translation Corpus](https://aclanthology.org/2026.lrec-1.564/) (Rapacz & Smywiński-Pohl, LREC 2026)
ACL