@inproceedings{kallas-etal-2024-emad-bridge,
title = "{EMAD}: A Bridge Tagset for Unifying {A}rabic {POS} Annotations",
author = "Kallas, Omar and
Inoue, Go and
Habash, Nizar",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.500",
pages = "5637--5643",
abstract = "There have been many attempts to model the morphological richness and complexity of Arabic, leading to numerous Part-of-Speech (POS) tagsets that differ in terms of (a) which morphological features they represent, (b) how they represent them, and (c) the degree of specification of said features. Tagset granularity plays an important role in determining how annotated data can be used and for what applications. Due to the diversity among existing tagsets, many annotated corpora for Arabic cannot be easily combined, which exacerbates the Arabic resource poverty situation. In this work, we propose an intermediate tagset designed to facilitate the conversion and unification of different tagsets used to annotate Arabic corpora. This new tagset acts as a bridge between different annotation schemes, simplifying the integration of annotated corpora and promoting collaboration across the projects using them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kallas-etal-2024-emad-bridge">
<titleInfo>
<title>EMAD: A Bridge Tagset for Unifying Arabic POS Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Kallas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There have been many attempts to model the morphological richness and complexity of Arabic, leading to numerous Part-of-Speech (POS) tagsets that differ in terms of (a) which morphological features they represent, (b) how they represent them, and (c) the degree of specification of said features. Tagset granularity plays an important role in determining how annotated data can be used and for what applications. Due to the diversity among existing tagsets, many annotated corpora for Arabic cannot be easily combined, which exacerbates the Arabic resource poverty situation. In this work, we propose an intermediate tagset designed to facilitate the conversion and unification of different tagsets used to annotate Arabic corpora. This new tagset acts as a bridge between different annotation schemes, simplifying the integration of annotated corpora and promoting collaboration across the projects using them.</abstract>
<identifier type="citekey">kallas-etal-2024-emad-bridge</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.500</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5637</start>
<end>5643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EMAD: A Bridge Tagset for Unifying Arabic POS Annotations
%A Kallas, Omar
%A Inoue, Go
%A Habash, Nizar
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kallas-etal-2024-emad-bridge
%X There have been many attempts to model the morphological richness and complexity of Arabic, leading to numerous Part-of-Speech (POS) tagsets that differ in terms of (a) which morphological features they represent, (b) how they represent them, and (c) the degree of specification of said features. Tagset granularity plays an important role in determining how annotated data can be used and for what applications. Due to the diversity among existing tagsets, many annotated corpora for Arabic cannot be easily combined, which exacerbates the Arabic resource poverty situation. In this work, we propose an intermediate tagset designed to facilitate the conversion and unification of different tagsets used to annotate Arabic corpora. This new tagset acts as a bridge between different annotation schemes, simplifying the integration of annotated corpora and promoting collaboration across the projects using them.
%U https://aclanthology.org/2024.lrec-main.500
%P 5637-5643
Markdown (Informal)
[EMAD: A Bridge Tagset for Unifying Arabic POS Annotations](https://aclanthology.org/2024.lrec-main.500) (Kallas et al., LREC-COLING 2024)
ACL
- Omar Kallas, Go Inoue, and Nizar Habash. 2024. EMAD: A Bridge Tagset for Unifying Arabic POS Annotations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5637–5643, Torino, Italia. ELRA and ICCL.