@inproceedings{6d31597b4177406ca6afac8fd578695b,
title = "EMAD: A Bridge Tagset for Unifying Arabic POS Annotations",
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.",
keywords = "annotation, Arabic, morphology, tagset",
author = "Omar Kallas and Go Inoue and Nizar Habash",
note = "Publisher Copyright: {\textcopyright} 2024 ELRA Language Resource Association: CC BY-NC 4.0.; Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 ; Conference date: 20-05-2024 Through 25-05-2024",
year = "2024",
language = "English (US)",
series = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "5637--5643",
editor = "Nicoletta Calzolari and Min-Yen Kan and Veronique Hoste and Alessandro Lenci and Sakriani Sakti and Nianwen Xue",
booktitle = "2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings",
}