@inproceedings{darwish-etal-2017-arabic-pos,
title = "{A}rabic {POS} Tagging: Don{'}t Abandon Feature Engineering Just Yet",
author = "Darwish, Kareem and
Mubarak, Hamdy and
Abdelali, Ahmed and
Eldesouki, Mohamed",
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/W17-1316",
doi = "10.18653/v1/W17-1316",
pages = "130--137",
abstract = "This paper focuses on comparing between using Support Vector Machine based ranking (SVM-Rank) and Bidirectional Long-Short-Term-Memory (bi-LSTM) neural-network based sequence labeling in building a state-of-the-art Arabic part-of-speech tagging system. Using SVM-Rank leads to state-of-the-art results, but with a fair amount of feature engineering. Using bi-LSTM, particularly when combined with word embeddings, may lead to competitive POS-tagging results by automatically deducing latent linguistic features. However, we show that augmenting bi-LSTM sequence labeling with some of the features that we used for the SVM-Rank based tagger yields to further improvements. We also show that gains that realized by using embeddings may not be additive with the gains achieved by the features. We are open-sourcing both the SVM-Rank and the bi-LSTM based systems for free.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="darwish-etal-2017-arabic-pos">
<titleInfo>
<title>Arabic POS Tagging: Don’t Abandon Feature Engineering Just Yet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</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">Mohamed</namePart>
<namePart type="family">Eldesouki</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 focuses on comparing between using Support Vector Machine based ranking (SVM-Rank) and Bidirectional Long-Short-Term-Memory (bi-LSTM) neural-network based sequence labeling in building a state-of-the-art Arabic part-of-speech tagging system. Using SVM-Rank leads to state-of-the-art results, but with a fair amount of feature engineering. Using bi-LSTM, particularly when combined with word embeddings, may lead to competitive POS-tagging results by automatically deducing latent linguistic features. However, we show that augmenting bi-LSTM sequence labeling with some of the features that we used for the SVM-Rank based tagger yields to further improvements. We also show that gains that realized by using embeddings may not be additive with the gains achieved by the features. We are open-sourcing both the SVM-Rank and the bi-LSTM based systems for free.</abstract>
<identifier type="citekey">darwish-etal-2017-arabic-pos</identifier>
<identifier type="doi">10.18653/v1/W17-1316</identifier>
<location>
<url>https://aclanthology.org/W17-1316</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>130</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic POS Tagging: Don’t Abandon Feature Engineering Just Yet
%A Darwish, Kareem
%A Mubarak, Hamdy
%A Abdelali, Ahmed
%A Eldesouki, Mohamed
%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 darwish-etal-2017-arabic-pos
%X This paper focuses on comparing between using Support Vector Machine based ranking (SVM-Rank) and Bidirectional Long-Short-Term-Memory (bi-LSTM) neural-network based sequence labeling in building a state-of-the-art Arabic part-of-speech tagging system. Using SVM-Rank leads to state-of-the-art results, but with a fair amount of feature engineering. Using bi-LSTM, particularly when combined with word embeddings, may lead to competitive POS-tagging results by automatically deducing latent linguistic features. However, we show that augmenting bi-LSTM sequence labeling with some of the features that we used for the SVM-Rank based tagger yields to further improvements. We also show that gains that realized by using embeddings may not be additive with the gains achieved by the features. We are open-sourcing both the SVM-Rank and the bi-LSTM based systems for free.
%R 10.18653/v1/W17-1316
%U https://aclanthology.org/W17-1316
%U https://doi.org/10.18653/v1/W17-1316
%P 130-137
Markdown (Informal)
[Arabic POS Tagging: Don’t Abandon Feature Engineering Just Yet](https://aclanthology.org/W17-1316) (Darwish et al., WANLP 2017)
ACL