@inproceedings{habash-etal-2016-exploiting,
title = "Exploiting {A}rabic Diacritization for High Quality Automatic Annotation",
author = "Habash, Nizar and
Shahrour, Anas and
Al-Khalil, Muhamed",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1681",
pages = "4298--4304",
abstract = "We present a novel technique for Arabic morphological annotation. The technique utilizes diacritization to produce morphological annotations of quality comparable to human annotators. Although Arabic text is generally written without diacritics, diacritization is already available for large corpora of Arabic text in several genres. Furthermore, diacritization can be generated at a low cost for new text as it does not require specialized training beyond what educated Arabic typists know. The basic approach is to enrich the input to a state-of-the-art Arabic morphological analyzer with word diacritics (full or partial) to enhance its performance. When applied to fully diacritized text, our approach produces annotations with an accuracy of over 97{\%} on lemma, part-of-speech, and tokenization combined.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="habash-etal-2016-exploiting">
<titleInfo>
<title>Exploiting Arabic Diacritization for High Quality Automatic Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="family">Shahrour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhamed</namePart>
<namePart type="family">Al-Khalil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a novel technique for Arabic morphological annotation. The technique utilizes diacritization to produce morphological annotations of quality comparable to human annotators. Although Arabic text is generally written without diacritics, diacritization is already available for large corpora of Arabic text in several genres. Furthermore, diacritization can be generated at a low cost for new text as it does not require specialized training beyond what educated Arabic typists know. The basic approach is to enrich the input to a state-of-the-art Arabic morphological analyzer with word diacritics (full or partial) to enhance its performance. When applied to fully diacritized text, our approach produces annotations with an accuracy of over 97% on lemma, part-of-speech, and tokenization combined.</abstract>
<identifier type="citekey">habash-etal-2016-exploiting</identifier>
<location>
<url>https://aclanthology.org/L16-1681</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4298</start>
<end>4304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Arabic Diacritization for High Quality Automatic Annotation
%A Habash, Nizar
%A Shahrour, Anas
%A Al-Khalil, Muhamed
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F habash-etal-2016-exploiting
%X We present a novel technique for Arabic morphological annotation. The technique utilizes diacritization to produce morphological annotations of quality comparable to human annotators. Although Arabic text is generally written without diacritics, diacritization is already available for large corpora of Arabic text in several genres. Furthermore, diacritization can be generated at a low cost for new text as it does not require specialized training beyond what educated Arabic typists know. The basic approach is to enrich the input to a state-of-the-art Arabic morphological analyzer with word diacritics (full or partial) to enhance its performance. When applied to fully diacritized text, our approach produces annotations with an accuracy of over 97% on lemma, part-of-speech, and tokenization combined.
%U https://aclanthology.org/L16-1681
%P 4298-4304
Markdown (Informal)
[Exploiting Arabic Diacritization for High Quality Automatic Annotation](https://aclanthology.org/L16-1681) (Habash et al., LREC 2016)
ACL