@inproceedings{dunn-edwards-brown-2024-geographically-informed,
title = "Geographically-Informed Language Identification",
author = "Dunn, Jonathan and
Edwards-Brown, Lane",
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.678",
pages = "7672--7682",
abstract = "This paper develops an approach to language identification in which the set of languages considered by the model depends on the geographic origin of the text in question. Given that many digital corpora can be geo-referenced at the country level, this paper formulates 16 region-specific models, each of which contains the languages expected to appear in countries within that region. These regional models also each include 31 widely-spoken international languages in order to ensure coverage of these linguae francae regardless of location. An upstream evaluation using traditional language identification testing data shows an improvement in f-score ranging from 1.7 points (Southeast Asia) to as much as 10.4 points (North Africa). A downstream evaluation on social media data shows that this improved performance has a significant impact on the language labels which are applied to large real-world corpora. The result is a highly-accurate model that covers 916 languages at a sample size of 50 characters, the performance improved by incorporating geographic information into the model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dunn-edwards-brown-2024-geographically-informed">
<titleInfo>
<title>Geographically-Informed Language Identification</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">Lane</namePart>
<namePart type="family">Edwards-Brown</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>This paper develops an approach to language identification in which the set of languages considered by the model depends on the geographic origin of the text in question. Given that many digital corpora can be geo-referenced at the country level, this paper formulates 16 region-specific models, each of which contains the languages expected to appear in countries within that region. These regional models also each include 31 widely-spoken international languages in order to ensure coverage of these linguae francae regardless of location. An upstream evaluation using traditional language identification testing data shows an improvement in f-score ranging from 1.7 points (Southeast Asia) to as much as 10.4 points (North Africa). A downstream evaluation on social media data shows that this improved performance has a significant impact on the language labels which are applied to large real-world corpora. The result is a highly-accurate model that covers 916 languages at a sample size of 50 characters, the performance improved by incorporating geographic information into the model.</abstract>
<identifier type="citekey">dunn-edwards-brown-2024-geographically-informed</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.678</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7672</start>
<end>7682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Geographically-Informed Language Identification
%A Dunn, Jonathan
%A Edwards-Brown, Lane
%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 dunn-edwards-brown-2024-geographically-informed
%X This paper develops an approach to language identification in which the set of languages considered by the model depends on the geographic origin of the text in question. Given that many digital corpora can be geo-referenced at the country level, this paper formulates 16 region-specific models, each of which contains the languages expected to appear in countries within that region. These regional models also each include 31 widely-spoken international languages in order to ensure coverage of these linguae francae regardless of location. An upstream evaluation using traditional language identification testing data shows an improvement in f-score ranging from 1.7 points (Southeast Asia) to as much as 10.4 points (North Africa). A downstream evaluation on social media data shows that this improved performance has a significant impact on the language labels which are applied to large real-world corpora. The result is a highly-accurate model that covers 916 languages at a sample size of 50 characters, the performance improved by incorporating geographic information into the model.
%U https://aclanthology.org/2024.lrec-main.678
%P 7672-7682
Markdown (Informal)
[Geographically-Informed Language Identification](https://aclanthology.org/2024.lrec-main.678) (Dunn & Edwards-Brown, LREC-COLING 2024)
ACL
- Jonathan Dunn and Lane Edwards-Brown. 2024. Geographically-Informed Language Identification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7672–7682, Torino, Italia. ELRA and ICCL.