@inproceedings{mohamed-kubler-2010-arabic,
title = "{A}rabic Part of Speech Tagging",
author = {Mohamed, Emad and
K{\"u}bler, Sandra},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf",
abstract = "Arabic is a morphologically rich language, which presents a challenge for part of speech tagging. In this paper, we compare two novel methods for POS tagging of Arabic without the use of gold standard word segmentation but with the full POS tagset of the Penn Arabic Treebank. The first approach uses complex tags that describe full words and does not require any word segmentation. The second approach is segmentation-based, using a machine learning segmenter. In this approach, the words are first segmented, then the segments are annotated with POS tags. Because of the word-based approach, we evaluate full word accuracy rather than segment accuracy. Word-based POS tagging yields better results than segment-based tagging (93.93{\%} vs. 93.41{\%}). Word based tagging also gives the best results on known words, the segmentation-based approach gives better results on unknown words. Combining both methods results in a word accuracy of 94.37{\%}, which is very close to the result obtained by using gold standard segmentation (94.91{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-kubler-2010-arabic">
<titleInfo>
<title>Arabic Part of Speech Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emad</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Arabic is a morphologically rich language, which presents a challenge for part of speech tagging. In this paper, we compare two novel methods for POS tagging of Arabic without the use of gold standard word segmentation but with the full POS tagset of the Penn Arabic Treebank. The first approach uses complex tags that describe full words and does not require any word segmentation. The second approach is segmentation-based, using a machine learning segmenter. In this approach, the words are first segmented, then the segments are annotated with POS tags. Because of the word-based approach, we evaluate full word accuracy rather than segment accuracy. Word-based POS tagging yields better results than segment-based tagging (93.93% vs. 93.41%). Word based tagging also gives the best results on known words, the segmentation-based approach gives better results on unknown words. Combining both methods results in a word accuracy of 94.37%, which is very close to the result obtained by using gold standard segmentation (94.91%).</abstract>
<identifier type="citekey">mohamed-kubler-2010-arabic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Part of Speech Tagging
%A Mohamed, Emad
%A Kübler, Sandra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F mohamed-kubler-2010-arabic
%X Arabic is a morphologically rich language, which presents a challenge for part of speech tagging. In this paper, we compare two novel methods for POS tagging of Arabic without the use of gold standard word segmentation but with the full POS tagset of the Penn Arabic Treebank. The first approach uses complex tags that describe full words and does not require any word segmentation. The second approach is segmentation-based, using a machine learning segmenter. In this approach, the words are first segmented, then the segments are annotated with POS tags. Because of the word-based approach, we evaluate full word accuracy rather than segment accuracy. Word-based POS tagging yields better results than segment-based tagging (93.93% vs. 93.41%). Word based tagging also gives the best results on known words, the segmentation-based approach gives better results on unknown words. Combining both methods results in a word accuracy of 94.37%, which is very close to the result obtained by using gold standard segmentation (94.91%).
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf
Markdown (Informal)
[Arabic Part of Speech Tagging](http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf) (Mohamed & Kübler, LREC 2010)
ACL
- Emad Mohamed and Sandra Kübler. 2010. Arabic Part of Speech Tagging. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).