@inproceedings{gillis-webber-tittel-2020-framework,
title = "A Framework for Shared Agreement of Language Tags beyond {ISO} 639",
author = "Gillis-Webber, Frances and
Tittel, Sabine",
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-1.408",
pages = "3333--3339",
abstract = "The identification and annotation of languages in an unambiguous and standardized way is essential for the description of linguistic data. It is the prerequisite for machine-based interpretation, aggregation, and re-use of the data with respect to different languages. This makes it a key aspect especially for Linked Data and the multilingual Semantic Web. The standard for language tags is defined by IETF{'}s BCP 47 and ISO 639 provides the language codes that are the tags{'} main constituents. However, for the identification of lesser-known languages, endangered languages, regional varieties or historical stages of a language, the ISO 639 codes are insufficient. Also, the optional language sub-tags compliant with BCP 47 do not offer a possibility fine-grained enough to represent linguistic variation. We propose a versatile pattern that extends the BCP 47 sub-tag {`}privateuse{'} and is, thus, able to overcome the limits of BCP 47 and ISO 639. Sufficient coverage of the pattern is demonstrated with the use case of linguistic Linked Data of the endangered Gascon language. We show how to use a URI shortcode for the extended sub-tag, making the length compliant with BCP 47. We achieve this with a web application and API developed to encode and decode the language tag.",
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="gillis-webber-tittel-2020-framework">
<titleInfo>
<title>A Framework for Shared Agreement of Language Tags beyond ISO 639</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frances</namePart>
<namePart type="family">Gillis-Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Tittel</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>The identification and annotation of languages in an unambiguous and standardized way is essential for the description of linguistic data. It is the prerequisite for machine-based interpretation, aggregation, and re-use of the data with respect to different languages. This makes it a key aspect especially for Linked Data and the multilingual Semantic Web. The standard for language tags is defined by IETF’s BCP 47 and ISO 639 provides the language codes that are the tags’ main constituents. However, for the identification of lesser-known languages, endangered languages, regional varieties or historical stages of a language, the ISO 639 codes are insufficient. Also, the optional language sub-tags compliant with BCP 47 do not offer a possibility fine-grained enough to represent linguistic variation. We propose a versatile pattern that extends the BCP 47 sub-tag ‘privateuse’ and is, thus, able to overcome the limits of BCP 47 and ISO 639. Sufficient coverage of the pattern is demonstrated with the use case of linguistic Linked Data of the endangered Gascon language. We show how to use a URI shortcode for the extended sub-tag, making the length compliant with BCP 47. We achieve this with a web application and API developed to encode and decode the language tag.</abstract>
<identifier type="citekey">gillis-webber-tittel-2020-framework</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.408</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3333</start>
<end>3339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Framework for Shared Agreement of Language Tags beyond ISO 639
%A Gillis-Webber, Frances
%A Tittel, Sabine
%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 gillis-webber-tittel-2020-framework
%X The identification and annotation of languages in an unambiguous and standardized way is essential for the description of linguistic data. It is the prerequisite for machine-based interpretation, aggregation, and re-use of the data with respect to different languages. This makes it a key aspect especially for Linked Data and the multilingual Semantic Web. The standard for language tags is defined by IETF’s BCP 47 and ISO 639 provides the language codes that are the tags’ main constituents. However, for the identification of lesser-known languages, endangered languages, regional varieties or historical stages of a language, the ISO 639 codes are insufficient. Also, the optional language sub-tags compliant with BCP 47 do not offer a possibility fine-grained enough to represent linguistic variation. We propose a versatile pattern that extends the BCP 47 sub-tag ‘privateuse’ and is, thus, able to overcome the limits of BCP 47 and ISO 639. Sufficient coverage of the pattern is demonstrated with the use case of linguistic Linked Data of the endangered Gascon language. We show how to use a URI shortcode for the extended sub-tag, making the length compliant with BCP 47. We achieve this with a web application and API developed to encode and decode the language tag.
%U https://aclanthology.org/2020.lrec-1.408
%P 3333-3339
Markdown (Informal)
[A Framework for Shared Agreement of Language Tags beyond ISO 639](https://aclanthology.org/2020.lrec-1.408) (Gillis-Webber & Tittel, LREC 2020)
ACL