@inproceedings{adouane-dobnik-2017-identification,
title = "Identification of Languages in {A}lgerian {A}rabic Multilingual Documents",
author = "Adouane, Wafia and
Dobnik, Simon",
editor = "Habash, Nizar and
Diab, Mona and
Darwish, Kareem and
El-Hajj, Wassim and
Al-Khalifa, Hend and
Bouamor, Houda and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Third {A}rabic Natural Language Processing Workshop",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1301",
doi = "10.18653/v1/W17-1301",
pages = "1--8",
abstract = "This paper presents a language identification system designed to detect the language of each word, in its context, in a multilingual documents as generated in social media by bilingual/multilingual communities, in our case speakers of Algerian Arabic. We frame the task as a sequence tagging problem and use supervised machine learning with standard methods like HMM and Ngram classification tagging. We also experiment with a lexicon-based method. Combining all the methods in a fall-back mechanism and introducing some linguistic rules, to deal with unseen tokens and ambiguous words, gives an overall accuracy of 93.14{\%}. Finally, we introduced rules for language identification from sequences of recognised words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adouane-dobnik-2017-identification">
<titleInfo>
<title>Identification of Languages in Algerian Arabic Multilingual Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wafia</namePart>
<namePart type="family">Adouane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</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">Wassim</namePart>
<namePart type="family">El-Hajj</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">Houda</namePart>
<namePart type="family">Bouamor</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">Mahmoud</namePart>
<namePart type="family">El-Haj</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">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a language identification system designed to detect the language of each word, in its context, in a multilingual documents as generated in social media by bilingual/multilingual communities, in our case speakers of Algerian Arabic. We frame the task as a sequence tagging problem and use supervised machine learning with standard methods like HMM and Ngram classification tagging. We also experiment with a lexicon-based method. Combining all the methods in a fall-back mechanism and introducing some linguistic rules, to deal with unseen tokens and ambiguous words, gives an overall accuracy of 93.14%. Finally, we introduced rules for language identification from sequences of recognised words.</abstract>
<identifier type="citekey">adouane-dobnik-2017-identification</identifier>
<identifier type="doi">10.18653/v1/W17-1301</identifier>
<location>
<url>https://aclanthology.org/W17-1301</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identification of Languages in Algerian Arabic Multilingual Documents
%A Adouane, Wafia
%A Dobnik, Simon
%Y Habash, Nizar
%Y Diab, Mona
%Y Darwish, Kareem
%Y El-Hajj, Wassim
%Y Al-Khalifa, Hend
%Y Bouamor, Houda
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Third Arabic Natural Language Processing Workshop
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F adouane-dobnik-2017-identification
%X This paper presents a language identification system designed to detect the language of each word, in its context, in a multilingual documents as generated in social media by bilingual/multilingual communities, in our case speakers of Algerian Arabic. We frame the task as a sequence tagging problem and use supervised machine learning with standard methods like HMM and Ngram classification tagging. We also experiment with a lexicon-based method. Combining all the methods in a fall-back mechanism and introducing some linguistic rules, to deal with unseen tokens and ambiguous words, gives an overall accuracy of 93.14%. Finally, we introduced rules for language identification from sequences of recognised words.
%R 10.18653/v1/W17-1301
%U https://aclanthology.org/W17-1301
%U https://doi.org/10.18653/v1/W17-1301
%P 1-8
Markdown (Informal)
[Identification of Languages in Algerian Arabic Multilingual Documents](https://aclanthology.org/W17-1301) (Adouane & Dobnik, WANLP 2017)
ACL