@inproceedings{zarnoufi-etal-2020-manorm,
title = "{MAN}orm: A Normalization Dictionary for {M}oroccan {A}rabic Dialect Written in {L}atin Script",
author = "Zarnoufi, Randa and
Jaafar, Hamid and
Bachri, Walid and
Abik, Mounia",
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-1.14/",
pages = "155--166",
abstract = "Social media user generated text is actually the main resource for many NLP tasks. This text, however, does not follow the standard rules of writing. Moreover, the use of dialect such as Moroccan Arabic in written communications increases further NLP tasks complexity. A dialect is a verbal language that does not have a standard orthography. The written dialect is based on the phonetic transliteration of spoken words which leads users to improvise spelling while writing. Thus, for the same word we can find multiple forms of transliterations. Subsequently, it is mandatory to normalize these different transliterations to one canonical word form. To reach this goal, we have exploited the powerfulness of word embedding models generated with a corpus of YouTube comments. Besides, using a Moroccan Arabic dialect dictionary that provides the canonical forms, we have built a normalization dictionary that we refer to as MANorm. We have conducted several experiments to demonstrate the efficiency of MANorm, which have shown its usefulness in dialect normalization. We made MANorm freely available online."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zarnoufi-etal-2020-manorm">
<titleInfo>
<title>MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script</title>
</titleInfo>
<name type="personal">
<namePart type="given">Randa</namePart>
<namePart type="family">Zarnoufi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamid</namePart>
<namePart type="family">Jaafar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Bachri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mounia</namePart>
<namePart type="family">Abik</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>Social media user generated text is actually the main resource for many NLP tasks. This text, however, does not follow the standard rules of writing. Moreover, the use of dialect such as Moroccan Arabic in written communications increases further NLP tasks complexity. A dialect is a verbal language that does not have a standard orthography. The written dialect is based on the phonetic transliteration of spoken words which leads users to improvise spelling while writing. Thus, for the same word we can find multiple forms of transliterations. Subsequently, it is mandatory to normalize these different transliterations to one canonical word form. To reach this goal, we have exploited the powerfulness of word embedding models generated with a corpus of YouTube comments. Besides, using a Moroccan Arabic dialect dictionary that provides the canonical forms, we have built a normalization dictionary that we refer to as MANorm. We have conducted several experiments to demonstrate the efficiency of MANorm, which have shown its usefulness in dialect normalization. We made MANorm freely available online.</abstract>
<identifier type="citekey">zarnoufi-etal-2020-manorm</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.14/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>155</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script
%A Zarnoufi, Randa
%A Jaafar, Hamid
%A Bachri, Walid
%A Abik, Mounia
%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 zarnoufi-etal-2020-manorm
%X Social media user generated text is actually the main resource for many NLP tasks. This text, however, does not follow the standard rules of writing. Moreover, the use of dialect such as Moroccan Arabic in written communications increases further NLP tasks complexity. A dialect is a verbal language that does not have a standard orthography. The written dialect is based on the phonetic transliteration of spoken words which leads users to improvise spelling while writing. Thus, for the same word we can find multiple forms of transliterations. Subsequently, it is mandatory to normalize these different transliterations to one canonical word form. To reach this goal, we have exploited the powerfulness of word embedding models generated with a corpus of YouTube comments. Besides, using a Moroccan Arabic dialect dictionary that provides the canonical forms, we have built a normalization dictionary that we refer to as MANorm. We have conducted several experiments to demonstrate the efficiency of MANorm, which have shown its usefulness in dialect normalization. We made MANorm freely available online.
%U https://aclanthology.org/2020.wanlp-1.14/
%P 155-166
Markdown (Informal)
[MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script](https://aclanthology.org/2020.wanlp-1.14/) (Zarnoufi et al., WANLP 2020)
ACL