@inproceedings{tawfik-etal-2019-morphology,
title = "Morphology-aware Word-Segmentation in Dialectal {A}rabic Adaptation of Neural Machine Translation",
author = "Tawfik, Ahmed and
Emam, Mahitab and
Essam, Khaled and
Nabil, Robert and
Hassan, Hany",
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/W19-4602",
doi = "10.18653/v1/W19-4602",
pages = "11--17",
abstract = "Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited. The scarcity of resources has prompted the use of Modern Standard Arabic (MSA) abundant resources to complement the limited dialectal resource. However, dialectal clitics often differ between MSA and DA. This paper compares morphology-aware DA word segmentation to other word segmentation approaches like Byte Pair Encoding (BPE) and Sub-word Regularization (SR). A set of experiments conducted on Egyptian Arabic (EA), Levantine Arabic (LA), and Gulf Arabic (GA) show that a sufficiently accurate morphology-aware segmentation used in conjunction with BPE outperforms the other word segmentation approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tawfik-etal-2019-morphology">
<titleInfo>
<title>Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Tawfik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahitab</namePart>
<namePart type="family">Emam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Essam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Nabil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hany</namePart>
<namePart type="family">Hassan</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>Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited. The scarcity of resources has prompted the use of Modern Standard Arabic (MSA) abundant resources to complement the limited dialectal resource. However, dialectal clitics often differ between MSA and DA. This paper compares morphology-aware DA word segmentation to other word segmentation approaches like Byte Pair Encoding (BPE) and Sub-word Regularization (SR). A set of experiments conducted on Egyptian Arabic (EA), Levantine Arabic (LA), and Gulf Arabic (GA) show that a sufficiently accurate morphology-aware segmentation used in conjunction with BPE outperforms the other word segmentation approaches.</abstract>
<identifier type="citekey">tawfik-etal-2019-morphology</identifier>
<identifier type="doi">10.18653/v1/W19-4602</identifier>
<location>
<url>https://aclanthology.org/W19-4602</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>11</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation
%A Tawfik, Ahmed
%A Emam, Mahitab
%A Essam, Khaled
%A Nabil, Robert
%A Hassan, Hany
%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 tawfik-etal-2019-morphology
%X Parallel corpora available for building machine translation (MT) models for dialectal Arabic (DA) are rather limited. The scarcity of resources has prompted the use of Modern Standard Arabic (MSA) abundant resources to complement the limited dialectal resource. However, dialectal clitics often differ between MSA and DA. This paper compares morphology-aware DA word segmentation to other word segmentation approaches like Byte Pair Encoding (BPE) and Sub-word Regularization (SR). A set of experiments conducted on Egyptian Arabic (EA), Levantine Arabic (LA), and Gulf Arabic (GA) show that a sufficiently accurate morphology-aware segmentation used in conjunction with BPE outperforms the other word segmentation approaches.
%R 10.18653/v1/W19-4602
%U https://aclanthology.org/W19-4602
%U https://doi.org/10.18653/v1/W19-4602
%P 11-17
Markdown (Informal)
[Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation](https://aclanthology.org/W19-4602) (Tawfik et al., WANLP 2019)
ACL