@inproceedings{dogruoz-etal-2021-survey,
title = "A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies",
author = {Do{\u{g}}ru{\"o}z, A. Seza and
Sitaram, Sunayana and
Bullock, Barbara E. and
Toribio, Almeida Jacqueline},
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.131",
doi = "10.18653/v1/2021.acl-long.131",
pages = "1654--1666",
abstract = "The analysis of data in which multiple languages are represented has gained popularity among computational linguists in recent years. So far, much of this research focuses mainly on the improvement of computational methods and largely ignores linguistic and social aspects of C-S discussed across a wide range of languages within the long-established literature in linguistics. To fill this gap, we offer a survey of code-switching (C-S) covering the literature in linguistics with a reflection on the key issues in language technologies. From the linguistic perspective, we provide an overview of structural and functional patterns of C-S focusing on the literature from European and Indian contexts as highly multilingual areas. From the language technologies perspective, we discuss how massive language models fail to represent diverse C-S types due to lack of appropriate training data, lack of robust evaluation benchmarks for C-S (across multilingual situations and types of C-S) and lack of end-to- end systems that cover sociolinguistic aspects of C-S as well. Our survey will be a step to- wards an outcome of mutual benefit for computational scientists and linguists with a shared interest in multilingualism and C-S.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dogruoz-etal-2021-survey">
<titleInfo>
<title>A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Bullock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Almeida</namePart>
<namePart type="given">Jacqueline</namePart>
<namePart type="family">Toribio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The analysis of data in which multiple languages are represented has gained popularity among computational linguists in recent years. So far, much of this research focuses mainly on the improvement of computational methods and largely ignores linguistic and social aspects of C-S discussed across a wide range of languages within the long-established literature in linguistics. To fill this gap, we offer a survey of code-switching (C-S) covering the literature in linguistics with a reflection on the key issues in language technologies. From the linguistic perspective, we provide an overview of structural and functional patterns of C-S focusing on the literature from European and Indian contexts as highly multilingual areas. From the language technologies perspective, we discuss how massive language models fail to represent diverse C-S types due to lack of appropriate training data, lack of robust evaluation benchmarks for C-S (across multilingual situations and types of C-S) and lack of end-to- end systems that cover sociolinguistic aspects of C-S as well. Our survey will be a step to- wards an outcome of mutual benefit for computational scientists and linguists with a shared interest in multilingualism and C-S.</abstract>
<identifier type="citekey">dogruoz-etal-2021-survey</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.131</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.131</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1654</start>
<end>1666</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies
%A Doğruöz, A. Seza
%A Sitaram, Sunayana
%A Bullock, Barbara E.
%A Toribio, Almeida Jacqueline
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F dogruoz-etal-2021-survey
%X The analysis of data in which multiple languages are represented has gained popularity among computational linguists in recent years. So far, much of this research focuses mainly on the improvement of computational methods and largely ignores linguistic and social aspects of C-S discussed across a wide range of languages within the long-established literature in linguistics. To fill this gap, we offer a survey of code-switching (C-S) covering the literature in linguistics with a reflection on the key issues in language technologies. From the linguistic perspective, we provide an overview of structural and functional patterns of C-S focusing on the literature from European and Indian contexts as highly multilingual areas. From the language technologies perspective, we discuss how massive language models fail to represent diverse C-S types due to lack of appropriate training data, lack of robust evaluation benchmarks for C-S (across multilingual situations and types of C-S) and lack of end-to- end systems that cover sociolinguistic aspects of C-S as well. Our survey will be a step to- wards an outcome of mutual benefit for computational scientists and linguists with a shared interest in multilingualism and C-S.
%R 10.18653/v1/2021.acl-long.131
%U https://aclanthology.org/2021.acl-long.131
%U https://doi.org/10.18653/v1/2021.acl-long.131
%P 1654-1666
Markdown (Informal)
[A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies](https://aclanthology.org/2021.acl-long.131) (Doğruöz et al., ACL-IJCNLP 2021)
ACL
- A. Seza Doğruöz, Sunayana Sitaram, Barbara E. Bullock, and Almeida Jacqueline Toribio. 2021. A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1654–1666, Online. Association for Computational Linguistics.