@inproceedings{attia-etal-2019-pos,
title = "{POS} Tagging for Improving Code-Switching Identification in {A}rabic",
author = "Attia, Mohammed and
Samih, Younes and
Elkahky, Ali and
Mubarak, Hamdy and
Abdelali, Ahmed and
Darwish, Kareem",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4603",
doi = "10.18653/v1/W19-4603",
pages = "18--29",
abstract = "When speakers code-switch between their native language and a second language or language variant, they follow a syntactic pattern where words and phrases from the embedded language are inserted into the matrix language. This paper explores the possibility of utilizing this pattern in improving code-switching identification between Modern Standard Arabic (MSA) and Egyptian Arabic (EA). We try to answer the question of how strong is the POS signal in word-level code-switching identification. We build a deep learning model enriched with linguistic features (including POS tags) that outperforms the state-of-the-art results by 1.9{\%} on the development set and 1.0{\%} on the test set. We also show that in intra-sentential code-switching, the selection of lexical items is constrained by POS categories, where function words tend to come more often from the dialectal language while the majority of content words come from the standard language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="attia-etal-2019-pos">
<titleInfo>
<title>POS Tagging for Improving Code-Switching Identification in Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Attia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Elkahky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<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">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</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">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">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">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When speakers code-switch between their native language and a second language or language variant, they follow a syntactic pattern where words and phrases from the embedded language are inserted into the matrix language. This paper explores the possibility of utilizing this pattern in improving code-switching identification between Modern Standard Arabic (MSA) and Egyptian Arabic (EA). We try to answer the question of how strong is the POS signal in word-level code-switching identification. We build a deep learning model enriched with linguistic features (including POS tags) that outperforms the state-of-the-art results by 1.9% on the development set and 1.0% on the test set. We also show that in intra-sentential code-switching, the selection of lexical items is constrained by POS categories, where function words tend to come more often from the dialectal language while the majority of content words come from the standard language.</abstract>
<identifier type="citekey">attia-etal-2019-pos</identifier>
<identifier type="doi">10.18653/v1/W19-4603</identifier>
<location>
<url>https://aclanthology.org/W19-4603</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>18</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POS Tagging for Improving Code-Switching Identification in Arabic
%A Attia, Mohammed
%A Samih, Younes
%A Elkahky, Ali
%A Mubarak, Hamdy
%A Abdelali, Ahmed
%A Darwish, Kareem
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F attia-etal-2019-pos
%X When speakers code-switch between their native language and a second language or language variant, they follow a syntactic pattern where words and phrases from the embedded language are inserted into the matrix language. This paper explores the possibility of utilizing this pattern in improving code-switching identification between Modern Standard Arabic (MSA) and Egyptian Arabic (EA). We try to answer the question of how strong is the POS signal in word-level code-switching identification. We build a deep learning model enriched with linguistic features (including POS tags) that outperforms the state-of-the-art results by 1.9% on the development set and 1.0% on the test set. We also show that in intra-sentential code-switching, the selection of lexical items is constrained by POS categories, where function words tend to come more often from the dialectal language while the majority of content words come from the standard language.
%R 10.18653/v1/W19-4603
%U https://aclanthology.org/W19-4603
%U https://doi.org/10.18653/v1/W19-4603
%P 18-29
Markdown (Informal)
[POS Tagging for Improving Code-Switching Identification in Arabic](https://aclanthology.org/W19-4603) (Attia et al., WANLP 2019)
ACL