@inproceedings{kann-2024-massively,
title = "Massively Multilingual Token-Based Typology Using the Parallel {B}ible Corpus",
author = "Kann, Amanda",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.965",
pages = "11070--11079",
abstract = "The parallel Bible corpus is a uniquely broad multilingual resource, covering over 1400 languages. While this data is potentially highly useful for extending language coverage in both token-based typology research and various low-resource NLP applications, the restricted register and translational nature of the Bible texts has raised concerns as to whether they are sufficiently representative of language use outside of their specific context. In this paper, we analyze the reliability and generalisability of word order statistics extracted from the Bible corpus from two angles: stability across different translations in the same language, and comparability with Universal Dependencies corpora and typological database classifications from URIEL and Grambank. We find that variation between same-language translations is generally low and that agreement with other data sources and previous work is generally high, suggesting that the impact of issues specific to massively parallel texts is smaller than previously posited.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kann-2024-massively">
<titleInfo>
<title>Massively Multilingual Token-Based Typology Using the Parallel Bible Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The parallel Bible corpus is a uniquely broad multilingual resource, covering over 1400 languages. While this data is potentially highly useful for extending language coverage in both token-based typology research and various low-resource NLP applications, the restricted register and translational nature of the Bible texts has raised concerns as to whether they are sufficiently representative of language use outside of their specific context. In this paper, we analyze the reliability and generalisability of word order statistics extracted from the Bible corpus from two angles: stability across different translations in the same language, and comparability with Universal Dependencies corpora and typological database classifications from URIEL and Grambank. We find that variation between same-language translations is generally low and that agreement with other data sources and previous work is generally high, suggesting that the impact of issues specific to massively parallel texts is smaller than previously posited.</abstract>
<identifier type="citekey">kann-2024-massively</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.965</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11070</start>
<end>11079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Massively Multilingual Token-Based Typology Using the Parallel Bible Corpus
%A Kann, Amanda
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kann-2024-massively
%X The parallel Bible corpus is a uniquely broad multilingual resource, covering over 1400 languages. While this data is potentially highly useful for extending language coverage in both token-based typology research and various low-resource NLP applications, the restricted register and translational nature of the Bible texts has raised concerns as to whether they are sufficiently representative of language use outside of their specific context. In this paper, we analyze the reliability and generalisability of word order statistics extracted from the Bible corpus from two angles: stability across different translations in the same language, and comparability with Universal Dependencies corpora and typological database classifications from URIEL and Grambank. We find that variation between same-language translations is generally low and that agreement with other data sources and previous work is generally high, suggesting that the impact of issues specific to massively parallel texts is smaller than previously posited.
%U https://aclanthology.org/2024.lrec-main.965
%P 11070-11079
Markdown (Informal)
[Massively Multilingual Token-Based Typology Using the Parallel Bible Corpus](https://aclanthology.org/2024.lrec-main.965) (Kann, LREC-COLING 2024)
ACL