@inproceedings{forkel-list-2020-cldfbench,
title = "{CLDFB}ench: Give Your Cross-Linguistic Data a Lift",
author = "Forkel, Robert and
List, Johann-Mattis",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.864",
pages = "6995--7002",
abstract = "While the amount of cross-linguistic data is constantly increasing, most datasets produced today and in the past cannot be considered FAIR (findable, accessible, interoperable, and reproducible). To remedy this and to increase the comparability of cross-linguistic resources, it is not enough to set up standards and best practices for data to be collected in the future. We also need consistent workflows for the {``}retro-standardization{''} of data that has been published during the past decades and centuries. With the Cross-Linguistic Data Formats initiative, first standards for cross-linguistic data have been presented and successfully tested. So far, however, CLDF creation was hampered by the fact that it required a considerable degree of computational proficiency. With cldfbench, we introduce a framework for the retro-standardization of legacy data and the curation of new datasets that drastically simplifies the creation of CLDF by providing a consistent, reproducible workflow that rigorously supports version control and long term archiving of research data and code. The framework is distributed in form of a Python package along with usage information and examples for best practice. This study introduces the new framework and illustrates how it can be applied by showing how a resource containing structural and lexical data for Sinitic languages can be efficiently retro-standardized and analyzed.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="forkel-list-2020-cldfbench">
<titleInfo>
<title>CLDFBench: Give Your Cross-Linguistic Data a Lift</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Forkel</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>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>While the amount of cross-linguistic data is constantly increasing, most datasets produced today and in the past cannot be considered FAIR (findable, accessible, interoperable, and reproducible). To remedy this and to increase the comparability of cross-linguistic resources, it is not enough to set up standards and best practices for data to be collected in the future. We also need consistent workflows for the “retro-standardization” of data that has been published during the past decades and centuries. With the Cross-Linguistic Data Formats initiative, first standards for cross-linguistic data have been presented and successfully tested. So far, however, CLDF creation was hampered by the fact that it required a considerable degree of computational proficiency. With cldfbench, we introduce a framework for the retro-standardization of legacy data and the curation of new datasets that drastically simplifies the creation of CLDF by providing a consistent, reproducible workflow that rigorously supports version control and long term archiving of research data and code. The framework is distributed in form of a Python package along with usage information and examples for best practice. This study introduces the new framework and illustrates how it can be applied by showing how a resource containing structural and lexical data for Sinitic languages can be efficiently retro-standardized and analyzed.</abstract>
<identifier type="citekey">forkel-list-2020-cldfbench</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.864</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6995</start>
<end>7002</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLDFBench: Give Your Cross-Linguistic Data a Lift
%A Forkel, Robert
%A List, Johann-Mattis
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F forkel-list-2020-cldfbench
%X While the amount of cross-linguistic data is constantly increasing, most datasets produced today and in the past cannot be considered FAIR (findable, accessible, interoperable, and reproducible). To remedy this and to increase the comparability of cross-linguistic resources, it is not enough to set up standards and best practices for data to be collected in the future. We also need consistent workflows for the “retro-standardization” of data that has been published during the past decades and centuries. With the Cross-Linguistic Data Formats initiative, first standards for cross-linguistic data have been presented and successfully tested. So far, however, CLDF creation was hampered by the fact that it required a considerable degree of computational proficiency. With cldfbench, we introduce a framework for the retro-standardization of legacy data and the curation of new datasets that drastically simplifies the creation of CLDF by providing a consistent, reproducible workflow that rigorously supports version control and long term archiving of research data and code. The framework is distributed in form of a Python package along with usage information and examples for best practice. This study introduces the new framework and illustrates how it can be applied by showing how a resource containing structural and lexical data for Sinitic languages can be efficiently retro-standardized and analyzed.
%U https://aclanthology.org/2020.lrec-1.864
%P 6995-7002
Markdown (Informal)
[CLDFBench: Give Your Cross-Linguistic Data a Lift](https://aclanthology.org/2020.lrec-1.864) (Forkel & List, LREC 2020)
ACL
- Robert Forkel and Johann-Mattis List. 2020. CLDFBench: Give Your Cross-Linguistic Data a Lift. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6995–7002, Marseille, France. European Language Resources Association.