@inproceedings{mubarak-etal-2019-highly,
title = "Highly Effective {A}rabic Diacritization using Sequence to Sequence Modeling",
author = "Mubarak, Hamdy and
Abdelali, Ahmed and
Sajjad, Hassan and
Samih, Younes and
Darwish, Kareem",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1248",
doi = "10.18653/v1/N19-1248",
pages = "2390--2395",
abstract = "Arabic text is typically written without short vowels (or diacritics). However, their presence is required for properly verbalizing Arabic and is hence essential for applications such as text to speech. There are two types of diacritics, namely core-word diacritics and case-endings. Most previous works on automatic Arabic diacritic recovery rely on a large number of manually engineered features, particularly for case-endings. In this work, we present a unified character level sequence-to-sequence deep learning model that recovers both types of diacritics without the use of explicit feature engineering. Specifically, we employ a standard neural machine translation setup on overlapping windows of words (broken down into characters), and then we use voting to select the most likely diacritized form of a word. The proposed model outperforms all previous state-of-the-art systems. Our best settings achieve a word error rate (WER) of 4.49{\%} compared to the state-of-the-art of 12.25{\%} on a standard dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2019-highly">
<titleInfo>
<title>Highly Effective Arabic Diacritization using Sequence to Sequence Modeling</title>
</titleInfo>
<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">Hassan</namePart>
<namePart type="family">Sajjad</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">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Arabic text is typically written without short vowels (or diacritics). However, their presence is required for properly verbalizing Arabic and is hence essential for applications such as text to speech. There are two types of diacritics, namely core-word diacritics and case-endings. Most previous works on automatic Arabic diacritic recovery rely on a large number of manually engineered features, particularly for case-endings. In this work, we present a unified character level sequence-to-sequence deep learning model that recovers both types of diacritics without the use of explicit feature engineering. Specifically, we employ a standard neural machine translation setup on overlapping windows of words (broken down into characters), and then we use voting to select the most likely diacritized form of a word. The proposed model outperforms all previous state-of-the-art systems. Our best settings achieve a word error rate (WER) of 4.49% compared to the state-of-the-art of 12.25% on a standard dataset.</abstract>
<identifier type="citekey">mubarak-etal-2019-highly</identifier>
<identifier type="doi">10.18653/v1/N19-1248</identifier>
<location>
<url>https://aclanthology.org/N19-1248</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2390</start>
<end>2395</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Highly Effective Arabic Diacritization using Sequence to Sequence Modeling
%A Mubarak, Hamdy
%A Abdelali, Ahmed
%A Sajjad, Hassan
%A Samih, Younes
%A Darwish, Kareem
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F mubarak-etal-2019-highly
%X Arabic text is typically written without short vowels (or diacritics). However, their presence is required for properly verbalizing Arabic and is hence essential for applications such as text to speech. There are two types of diacritics, namely core-word diacritics and case-endings. Most previous works on automatic Arabic diacritic recovery rely on a large number of manually engineered features, particularly for case-endings. In this work, we present a unified character level sequence-to-sequence deep learning model that recovers both types of diacritics without the use of explicit feature engineering. Specifically, we employ a standard neural machine translation setup on overlapping windows of words (broken down into characters), and then we use voting to select the most likely diacritized form of a word. The proposed model outperforms all previous state-of-the-art systems. Our best settings achieve a word error rate (WER) of 4.49% compared to the state-of-the-art of 12.25% on a standard dataset.
%R 10.18653/v1/N19-1248
%U https://aclanthology.org/N19-1248
%U https://doi.org/10.18653/v1/N19-1248
%P 2390-2395
Markdown (Informal)
[Highly Effective Arabic Diacritization using Sequence to Sequence Modeling](https://aclanthology.org/N19-1248) (Mubarak et al., NAACL 2019)
ACL
- Hamdy Mubarak, Ahmed Abdelali, Hassan Sajjad, Younes Samih, and Kareem Darwish. 2019. Highly Effective Arabic Diacritization using Sequence to Sequence Modeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2390–2395, Minneapolis, Minnesota. Association for Computational Linguistics.