@inproceedings{dunn-nijhof-2022-language,
title = "Language Identification for {A}ustronesian Languages",
author = "Dunn, Jonathan and
Nijhof, Wikke",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.701",
pages = "6530--6539",
abstract = "This paper provides language identification models for low- and under-resourced languages in the Pacific region with a focus on previously unavailable Austronesian languages. Accurate language identification is an important part of developing language resources. The approach taken in this paper combines 29 Austronesian languages with 171 non-Austronesian languages to create an evaluation set drawn from eight data sources. After evaluating six approaches to language identification, we find that a classifier based on skip-gram embeddings reaches a significantly higher performance than alternate methods. We then systematically increase the number of non-Austronesian languages in the model up to a total of 800 languages to evaluate whether an increased language inventory leads to less precise predictions for the Austronesian languages of interest. This evaluation finds that there is only a minimal impact on accuracy caused by increasing the inventory of non-Austronesian languages. Further experiments adapt these language identification models for code-switching detection, achieving high accuracy across all 29 languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dunn-nijhof-2022-language">
<titleInfo>
<title>Language Identification for Austronesian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Dunn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wikke</namePart>
<namePart type="family">Nijhof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>This paper provides language identification models for low- and under-resourced languages in the Pacific region with a focus on previously unavailable Austronesian languages. Accurate language identification is an important part of developing language resources. The approach taken in this paper combines 29 Austronesian languages with 171 non-Austronesian languages to create an evaluation set drawn from eight data sources. After evaluating six approaches to language identification, we find that a classifier based on skip-gram embeddings reaches a significantly higher performance than alternate methods. We then systematically increase the number of non-Austronesian languages in the model up to a total of 800 languages to evaluate whether an increased language inventory leads to less precise predictions for the Austronesian languages of interest. This evaluation finds that there is only a minimal impact on accuracy caused by increasing the inventory of non-Austronesian languages. Further experiments adapt these language identification models for code-switching detection, achieving high accuracy across all 29 languages.</abstract>
<identifier type="citekey">dunn-nijhof-2022-language</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.701</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6530</start>
<end>6539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Identification for Austronesian Languages
%A Dunn, Jonathan
%A Nijhof, Wikke
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F dunn-nijhof-2022-language
%X This paper provides language identification models for low- and under-resourced languages in the Pacific region with a focus on previously unavailable Austronesian languages. Accurate language identification is an important part of developing language resources. The approach taken in this paper combines 29 Austronesian languages with 171 non-Austronesian languages to create an evaluation set drawn from eight data sources. After evaluating six approaches to language identification, we find that a classifier based on skip-gram embeddings reaches a significantly higher performance than alternate methods. We then systematically increase the number of non-Austronesian languages in the model up to a total of 800 languages to evaluate whether an increased language inventory leads to less precise predictions for the Austronesian languages of interest. This evaluation finds that there is only a minimal impact on accuracy caused by increasing the inventory of non-Austronesian languages. Further experiments adapt these language identification models for code-switching detection, achieving high accuracy across all 29 languages.
%U https://aclanthology.org/2022.lrec-1.701
%P 6530-6539
Markdown (Informal)
[Language Identification for Austronesian Languages](https://aclanthology.org/2022.lrec-1.701) (Dunn & Nijhof, LREC 2022)
ACL