@inproceedings{burchell-etal-2024-code,
title = "Code-Switched Language Identification is Harder Than You Think",
author = "Burchell, Laurie and
Birch, Alexandra and
Thompson, Robert and
Heafield, Kenneth",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.38",
pages = "646--658",
abstract = "Code switching (CS) is a very common phenomenon in written and spoken communication, but is handled poorly by many NLP applications. Looking to the application of building CS corpora, we explore CS language identification for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable architectures for this task and define metrics which better reflect desired performance. We present empirical evidence that no current approach is adequate, and finally provide recommendations for future work in this area.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burchell-etal-2024-code">
<titleInfo>
<title>Code-Switched Language Identification is Harder Than You Think</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Burchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code switching (CS) is a very common phenomenon in written and spoken communication, but is handled poorly by many NLP applications. Looking to the application of building CS corpora, we explore CS language identification for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable architectures for this task and define metrics which better reflect desired performance. We present empirical evidence that no current approach is adequate, and finally provide recommendations for future work in this area.</abstract>
<identifier type="citekey">burchell-etal-2024-code</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.38</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>646</start>
<end>658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Switched Language Identification is Harder Than You Think
%A Burchell, Laurie
%A Birch, Alexandra
%A Thompson, Robert
%A Heafield, Kenneth
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F burchell-etal-2024-code
%X Code switching (CS) is a very common phenomenon in written and spoken communication, but is handled poorly by many NLP applications. Looking to the application of building CS corpora, we explore CS language identification for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable architectures for this task and define metrics which better reflect desired performance. We present empirical evidence that no current approach is adequate, and finally provide recommendations for future work in this area.
%U https://aclanthology.org/2024.eacl-long.38
%P 646-658
Markdown (Informal)
[Code-Switched Language Identification is Harder Than You Think](https://aclanthology.org/2024.eacl-long.38) (Burchell et al., EACL 2024)
ACL
- Laurie Burchell, Alexandra Birch, Robert Thompson, and Kenneth Heafield. 2024. Code-Switched Language Identification is Harder Than You Think. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 646–658, St. Julian’s, Malta. Association for Computational Linguistics.