@inproceedings{shazal-etal-2020-unified,
title = "A Unified Model for {A}rabizi Detection and Transliteration using Sequence-to-Sequence Models",
author = "Shazal, Ali and
Usman, Aiza and
Habash, Nizar",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.15/",
pages = "167--177",
abstract = "While online Arabic is primarily written using the Arabic script, a Roman-script variety called Arabizi is often seen on social media. Although this representation captures the phonology of the language, it is not a one-to-one mapping with the Arabic script version. This issue is exacerbated by the fact that Arabizi on social media is Dialectal Arabic which does not have a standard orthography. Furthermore, Arabizi tends to include a lot of code mixing between Arabic and English (or French). To map Arabizi text to Arabic script in the context of complete utterances, previously published efforts have split Arabizi detection and Arabic script target in two separate tasks. In this paper, we present the first effort on a unified model for Arabizi detection and transliteration into a code-mixed output with consistent Arabic spelling conventions, using a sequence-to-sequence deep learning model. Our best system achieves 80.6{\%} word accuracy and 58.7{\%} BLEU on a blind test set."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shazal-etal-2020-unified">
<titleInfo>
<title>A Unified Model for Arabizi Detection and Transliteration using Sequence-to-Sequence Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Shazal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiza</namePart>
<namePart type="family">Usman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</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">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">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While online Arabic is primarily written using the Arabic script, a Roman-script variety called Arabizi is often seen on social media. Although this representation captures the phonology of the language, it is not a one-to-one mapping with the Arabic script version. This issue is exacerbated by the fact that Arabizi on social media is Dialectal Arabic which does not have a standard orthography. Furthermore, Arabizi tends to include a lot of code mixing between Arabic and English (or French). To map Arabizi text to Arabic script in the context of complete utterances, previously published efforts have split Arabizi detection and Arabic script target in two separate tasks. In this paper, we present the first effort on a unified model for Arabizi detection and transliteration into a code-mixed output with consistent Arabic spelling conventions, using a sequence-to-sequence deep learning model. Our best system achieves 80.6% word accuracy and 58.7% BLEU on a blind test set.</abstract>
<identifier type="citekey">shazal-etal-2020-unified</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.15/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>167</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Model for Arabizi Detection and Transliteration using Sequence-to-Sequence Models
%A Shazal, Ali
%A Usman, Aiza
%A Habash, Nizar
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F shazal-etal-2020-unified
%X While online Arabic is primarily written using the Arabic script, a Roman-script variety called Arabizi is often seen on social media. Although this representation captures the phonology of the language, it is not a one-to-one mapping with the Arabic script version. This issue is exacerbated by the fact that Arabizi on social media is Dialectal Arabic which does not have a standard orthography. Furthermore, Arabizi tends to include a lot of code mixing between Arabic and English (or French). To map Arabizi text to Arabic script in the context of complete utterances, previously published efforts have split Arabizi detection and Arabic script target in two separate tasks. In this paper, we present the first effort on a unified model for Arabizi detection and transliteration into a code-mixed output with consistent Arabic spelling conventions, using a sequence-to-sequence deep learning model. Our best system achieves 80.6% word accuracy and 58.7% BLEU on a blind test set.
%U https://aclanthology.org/2020.wanlp-1.15/
%P 167-177
Markdown (Informal)
[A Unified Model for Arabizi Detection and Transliteration using Sequence-to-Sequence Models](https://aclanthology.org/2020.wanlp-1.15/) (Shazal et al., WANLP 2020)
ACL