@inproceedings{sawalha-atwell-2010-constructing,
title = "Constructing and Using Broad-coverage Lexical Resource for Enhancing Morphological Analysis of {A}rabic",
author = "Sawalha, Majdi and
Atwell, Eric",
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 = "https://aclanthology.org/L10-1200/",
abstract = "Broad-coverage language resources which provide prior linguistic knowledge must improve the accuracy and the performance of NLP applications. We are constructing a broad-coverage lexical resource to improve the accuracy of morphological analyzers and part-of-speech taggers of Arabic text. Over the past 1200 years, many different kinds of Arabic language lexicons were constructed; these lexicons are different in ordering, size and aim or goal of construction. We collected 23 machine-readable lexicons, which are freely available on the web. We combined lexical resources into one large broad-coverage lexical resource by extracting information from disparate formats and merging traditional Arabic lexicons. To evaluate the broad-coverage lexical resource we computed coverage over the Quran, the Corpus of Contemporary Arabic, and a sample from the Arabic Web Corpus, using two methods. Counting exact word matches between test corpora and lexicon scored about 65-68{\%}; Arabic has a rich morphology with many combinations of roots, affixes and clitics, so about a third of words in the corpora did not have an exact match in the lexicon. The second approach is to compute coverage in terms of use in a lemmatizer program, which strips clitics to look for a match for the underlying lexeme; this scored about 82-85{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawalha-atwell-2010-constructing">
<titleInfo>
<title>Constructing and Using Broad-coverage Lexical Resource for Enhancing Morphological Analysis of Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Atwell</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>Broad-coverage language resources which provide prior linguistic knowledge must improve the accuracy and the performance of NLP applications. We are constructing a broad-coverage lexical resource to improve the accuracy of morphological analyzers and part-of-speech taggers of Arabic text. Over the past 1200 years, many different kinds of Arabic language lexicons were constructed; these lexicons are different in ordering, size and aim or goal of construction. We collected 23 machine-readable lexicons, which are freely available on the web. We combined lexical resources into one large broad-coverage lexical resource by extracting information from disparate formats and merging traditional Arabic lexicons. To evaluate the broad-coverage lexical resource we computed coverage over the Quran, the Corpus of Contemporary Arabic, and a sample from the Arabic Web Corpus, using two methods. Counting exact word matches between test corpora and lexicon scored about 65-68%; Arabic has a rich morphology with many combinations of roots, affixes and clitics, so about a third of words in the corpora did not have an exact match in the lexicon. The second approach is to compute coverage in terms of use in a lemmatizer program, which strips clitics to look for a match for the underlying lexeme; this scored about 82-85%.</abstract>
<identifier type="citekey">sawalha-atwell-2010-constructing</identifier>
<location>
<url>https://aclanthology.org/L10-1200/</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing and Using Broad-coverage Lexical Resource for Enhancing Morphological Analysis of Arabic
%A Sawalha, Majdi
%A Atwell, Eric
%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 sawalha-atwell-2010-constructing
%X Broad-coverage language resources which provide prior linguistic knowledge must improve the accuracy and the performance of NLP applications. We are constructing a broad-coverage lexical resource to improve the accuracy of morphological analyzers and part-of-speech taggers of Arabic text. Over the past 1200 years, many different kinds of Arabic language lexicons were constructed; these lexicons are different in ordering, size and aim or goal of construction. We collected 23 machine-readable lexicons, which are freely available on the web. We combined lexical resources into one large broad-coverage lexical resource by extracting information from disparate formats and merging traditional Arabic lexicons. To evaluate the broad-coverage lexical resource we computed coverage over the Quran, the Corpus of Contemporary Arabic, and a sample from the Arabic Web Corpus, using two methods. Counting exact word matches between test corpora and lexicon scored about 65-68%; Arabic has a rich morphology with many combinations of roots, affixes and clitics, so about a third of words in the corpora did not have an exact match in the lexicon. The second approach is to compute coverage in terms of use in a lemmatizer program, which strips clitics to look for a match for the underlying lexeme; this scored about 82-85%.
%U https://aclanthology.org/L10-1200/
Markdown (Informal)
[Constructing and Using Broad-coverage Lexical Resource for Enhancing Morphological Analysis of Arabic](https://aclanthology.org/L10-1200/) (Sawalha & Atwell, LREC 2010)
ACL