@inproceedings{mohamed-2012-morphological,
title = "Morphological Segmentation and Part of Speech Tagging for Religious {A}rabic",
author = "Mohamed, Emad",
editor = "Farghaly, Ali and
Oroumchian, Farhad",
booktitle = "Fourth Workshop on Computational Approaches to Arabic-Script-based Languages",
month = nov # " 1",
year = "2012",
address = "San Diego, California, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2012.amta-caas14.9",
pages = "65--71",
abstract = "We annotate a small corpus of religious Arabic with morphological segmentation boundaries and fine-grained segment-based part of speech tags. Experiments on both segmentation and POS tagging show that the religious corpus-trained segmenter and POS tagger outperform the Arabic Treebak-trained ones although the latter is 21 times as big, which shows the need for building religious Arabic linguistic resources. The small corpus we annotate improves segmentation accuracy by 5{\%} absolute (from 90.84{\%} to 95.70{\%}), and POS tagging by 9{\%} absolute (from 82.22{\%} to 91.26) when using gold standard segmentation, and by 9.6{\%} absolute (from 78.62{\%} to 88.22) when using automatic segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-2012-morphological">
<titleInfo>
<title>Morphological Segmentation and Part of Speech Tagging for Religious Arabic</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>
<originInfo>
<dateIssued>2012-nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Fourth Workshop on Computational Approaches to Arabic-Script-based Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Farghaly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Oroumchian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We annotate a small corpus of religious Arabic with morphological segmentation boundaries and fine-grained segment-based part of speech tags. Experiments on both segmentation and POS tagging show that the religious corpus-trained segmenter and POS tagger outperform the Arabic Treebak-trained ones although the latter is 21 times as big, which shows the need for building religious Arabic linguistic resources. The small corpus we annotate improves segmentation accuracy by 5% absolute (from 90.84% to 95.70%), and POS tagging by 9% absolute (from 82.22% to 91.26) when using gold standard segmentation, and by 9.6% absolute (from 78.62% to 88.22) when using automatic segmentation.</abstract>
<identifier type="citekey">mohamed-2012-morphological</identifier>
<location>
<url>https://aclanthology.org/2012.amta-caas14.9</url>
</location>
<part>
<date>2012-nov 1</date>
<extent unit="page">
<start>65</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphological Segmentation and Part of Speech Tagging for Religious Arabic
%A Mohamed, Emad
%Y Farghaly, Ali
%Y Oroumchian, Farhad
%S Fourth Workshop on Computational Approaches to Arabic-Script-based Languages
%D 2012
%8 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F mohamed-2012-morphological
%X We annotate a small corpus of religious Arabic with morphological segmentation boundaries and fine-grained segment-based part of speech tags. Experiments on both segmentation and POS tagging show that the religious corpus-trained segmenter and POS tagger outperform the Arabic Treebak-trained ones although the latter is 21 times as big, which shows the need for building religious Arabic linguistic resources. The small corpus we annotate improves segmentation accuracy by 5% absolute (from 90.84% to 95.70%), and POS tagging by 9% absolute (from 82.22% to 91.26) when using gold standard segmentation, and by 9.6% absolute (from 78.62% to 88.22) when using automatic segmentation.
%U https://aclanthology.org/2012.amta-caas14.9
%P 65-71
Markdown (Informal)
[Morphological Segmentation and Part of Speech Tagging for Religious Arabic](https://aclanthology.org/2012.amta-caas14.9) (Mohamed, AMTA 2012)
ACL