@inproceedings{shehadi-wintner-2022-identifying,
title = "Identifying Code-switching in {A}rabizi",
author = "Shehadi, Safaa and
Wintner, Shuly",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.18",
doi = "10.18653/v1/2022.wanlp-1.18",
pages = "194--204",
abstract = "We describe a corpus of social media posts that include utterances in Arabizi, a Roman-script rendering of Arabic, mixed with other languages, notably English, French, and Arabic written in the Arabic script. We manually annotated a subset of the texts with word-level language IDs; this is a non-trivial task due to the nature of mixed-language writing, especially on social media. We developed classifiers that can accurately predict the language ID tags. Then, we extended the word-level predictions to identify sentences that include Arabizi (and code-switching), and applied the classifiers to the raw corpus, thereby harvesting a large number of additional instances. The result is a large-scale dataset of Arabizi, with precise indications of code-switching between Arabizi and English, French, and Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shehadi-wintner-2022-identifying">
<titleInfo>
<title>Identifying Code-switching in Arabizi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Safaa</namePart>
<namePart type="family">Shehadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuly</namePart>
<namePart type="family">Wintner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe a corpus of social media posts that include utterances in Arabizi, a Roman-script rendering of Arabic, mixed with other languages, notably English, French, and Arabic written in the Arabic script. We manually annotated a subset of the texts with word-level language IDs; this is a non-trivial task due to the nature of mixed-language writing, especially on social media. We developed classifiers that can accurately predict the language ID tags. Then, we extended the word-level predictions to identify sentences that include Arabizi (and code-switching), and applied the classifiers to the raw corpus, thereby harvesting a large number of additional instances. The result is a large-scale dataset of Arabizi, with precise indications of code-switching between Arabizi and English, French, and Arabic.</abstract>
<identifier type="citekey">shehadi-wintner-2022-identifying</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.18</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.18</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>194</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Code-switching in Arabizi
%A Shehadi, Safaa
%A Wintner, Shuly
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F shehadi-wintner-2022-identifying
%X We describe a corpus of social media posts that include utterances in Arabizi, a Roman-script rendering of Arabic, mixed with other languages, notably English, French, and Arabic written in the Arabic script. We manually annotated a subset of the texts with word-level language IDs; this is a non-trivial task due to the nature of mixed-language writing, especially on social media. We developed classifiers that can accurately predict the language ID tags. Then, we extended the word-level predictions to identify sentences that include Arabizi (and code-switching), and applied the classifiers to the raw corpus, thereby harvesting a large number of additional instances. The result is a large-scale dataset of Arabizi, with precise indications of code-switching between Arabizi and English, French, and Arabic.
%R 10.18653/v1/2022.wanlp-1.18
%U https://aclanthology.org/2022.wanlp-1.18
%U https://doi.org/10.18653/v1/2022.wanlp-1.18
%P 194-204
Markdown (Informal)
[Identifying Code-switching in Arabizi](https://aclanthology.org/2022.wanlp-1.18) (Shehadi & Wintner, WANLP 2022)
ACL
- Safaa Shehadi and Shuly Wintner. 2022. Identifying Code-switching in Arabizi. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 194–204, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.