<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-mubarak-2025-advancing">
    <titleInfo>
        <title>Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abubakr</namePart>
        <namePart type="family">Mohamed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hamdy</namePart>
        <namePart type="family">Mubarak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Arabic diacritics, similar to short vowels in English, provide phonetic and grammatical information but are typically omitted in written Arabic, leading to ambiguity. Diacritization (aka diacritic restoration or vowelization) is essential for natural language processing. This paper advances Arabic diacritization through the following contributions: first, we propose a methodology to analyze and refine a large diacritized corpus to improve training quality. Second, we introduce WikiNews-2024, a multi-reference evaluation methodology with an updated version of the standard benchmark “WikiNews-2014”. In addition, we explore various model architectures and propose a BiLSTM-based model that achieves state-of-the-art results with 3.12% and 2.70% WER on WikiNews-2014 and WikiNews-2024, respectively. Moreover, we develop a model that preserves user-specified diacritics while maintaining accuracy. Lastly, we demonstrate that augmenting training data enhances performance in low-resource settings.</abstract>
    <identifier type="citekey">mohamed-mubarak-2025-advancing</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.846/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>16718</start>
            <end>16730</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models
%A Mohamed, Abubakr
%A Mubarak, Hamdy
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F mohamed-mubarak-2025-advancing
%X Arabic diacritics, similar to short vowels in English, provide phonetic and grammatical information but are typically omitted in written Arabic, leading to ambiguity. Diacritization (aka diacritic restoration or vowelization) is essential for natural language processing. This paper advances Arabic diacritization through the following contributions: first, we propose a methodology to analyze and refine a large diacritized corpus to improve training quality. Second, we introduce WikiNews-2024, a multi-reference evaluation methodology with an updated version of the standard benchmark “WikiNews-2014”. In addition, we explore various model architectures and propose a BiLSTM-based model that achieves state-of-the-art results with 3.12% and 2.70% WER on WikiNews-2014 and WikiNews-2024, respectively. Moreover, we develop a model that preserves user-specified diacritics while maintaining accuracy. Lastly, we demonstrate that augmenting training data enhances performance in low-resource settings.
%U https://aclanthology.org/2025.emnlp-main.846/
%P 16718-16730

Markdown (Informal)

[Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models](https://aclanthology.org/2025.emnlp-main.846/) (Mohamed & Mubarak, EMNLP 2025)

• Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models (Mohamed & Mubarak, EMNLP 2025)

ACL

• Abubakr Mohamed and Hamdy Mubarak. 2025. Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 16718–16730, Suzhou, China. Association for Computational Linguistics.