@inproceedings{alkhairy-etal-2020-finite,
title = "Finite State Machine Pattern-Root {A}rabic Morphological Generator, Analyzer and Diacritizer",
author = "Alkhairy, Maha and
Jafri, Afshan and
Smith, David",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.473",
pages = "3834--3841",
abstract = "We describe and evaluate the Finite-State Arabic Morphologizer (FSAM) {--} a concatenative (prefix-stem-suffix) and templatic (root- pattern) morphologizer that generates and analyzes undiacritized Modern Standard Arabic (MSA) words, and diacritizes them. Our bidirectional unified-architecture finite state machine (FSM) is based on morphotactic MSA grammatical rules. The FSM models the root-pattern structure related to semantics and syntax, making it readily scalable unlike stem-tabulations in prevailing systems. We evaluate the coverage and accuracy of our model, with coverage being percentage of words in Tashkeela (a large corpus) that can be analyzed. Accuracy is computed against a gold standard, comprising words and properties, created from the intersection of UD PADT treebank and Tashkeela. Coverage of analysis (extraction of root and properties from word) is 82{\%}. Accuracy results are: root computed from a word (92{\%}), word generation from a root (100{\%}), non-root properties of a word (97{\%}), and diacritization (84{\%}). FSAM{'}s non-root results match or surpass MADAMIRA{'}s, and root result comparisons are not made because of the concatenative nature of publicly available morphologizers.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkhairy-etal-2020-finite">
<titleInfo>
<title>Finite State Machine Pattern-Root Arabic Morphological Generator, Analyzer and Diacritizer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Alkhairy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshan</namePart>
<namePart type="family">Jafri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We describe and evaluate the Finite-State Arabic Morphologizer (FSAM) – a concatenative (prefix-stem-suffix) and templatic (root- pattern) morphologizer that generates and analyzes undiacritized Modern Standard Arabic (MSA) words, and diacritizes them. Our bidirectional unified-architecture finite state machine (FSM) is based on morphotactic MSA grammatical rules. The FSM models the root-pattern structure related to semantics and syntax, making it readily scalable unlike stem-tabulations in prevailing systems. We evaluate the coverage and accuracy of our model, with coverage being percentage of words in Tashkeela (a large corpus) that can be analyzed. Accuracy is computed against a gold standard, comprising words and properties, created from the intersection of UD PADT treebank and Tashkeela. Coverage of analysis (extraction of root and properties from word) is 82%. Accuracy results are: root computed from a word (92%), word generation from a root (100%), non-root properties of a word (97%), and diacritization (84%). FSAM’s non-root results match or surpass MADAMIRA’s, and root result comparisons are not made because of the concatenative nature of publicly available morphologizers.</abstract>
<identifier type="citekey">alkhairy-etal-2020-finite</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.473</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3834</start>
<end>3841</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finite State Machine Pattern-Root Arabic Morphological Generator, Analyzer and Diacritizer
%A Alkhairy, Maha
%A Jafri, Afshan
%A Smith, David
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F alkhairy-etal-2020-finite
%X We describe and evaluate the Finite-State Arabic Morphologizer (FSAM) – a concatenative (prefix-stem-suffix) and templatic (root- pattern) morphologizer that generates and analyzes undiacritized Modern Standard Arabic (MSA) words, and diacritizes them. Our bidirectional unified-architecture finite state machine (FSM) is based on morphotactic MSA grammatical rules. The FSM models the root-pattern structure related to semantics and syntax, making it readily scalable unlike stem-tabulations in prevailing systems. We evaluate the coverage and accuracy of our model, with coverage being percentage of words in Tashkeela (a large corpus) that can be analyzed. Accuracy is computed against a gold standard, comprising words and properties, created from the intersection of UD PADT treebank and Tashkeela. Coverage of analysis (extraction of root and properties from word) is 82%. Accuracy results are: root computed from a word (92%), word generation from a root (100%), non-root properties of a word (97%), and diacritization (84%). FSAM’s non-root results match or surpass MADAMIRA’s, and root result comparisons are not made because of the concatenative nature of publicly available morphologizers.
%U https://aclanthology.org/2020.lrec-1.473
%P 3834-3841
Markdown (Informal)
[Finite State Machine Pattern-Root Arabic Morphological Generator, Analyzer and Diacritizer](https://aclanthology.org/2020.lrec-1.473) (Alkhairy et al., LREC 2020)
ACL