@inproceedings{ali-alblooshi-etal-2025-uncertainty,
title = "Uncertainty-driven Partial Diacritization for {A}rabic Text",
author = "Ali Alblooshi, Humaid and
Shelmanov, Artem and
Aldarmaki, Hanan",
editor = "Noidea, Noidea",
booktitle = "Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.uncertainlp-main.1/",
pages = "1--10",
ISBN = "979-8-89176-349-4",
abstract = "We present an uncertainty-based approach to Partial Diacritization (PD) for Arabic text. We evaluate three uncertainty metrics for this task: Softmax Response, BALD via MC-dropout, and Mahalanobis Distance. We further introduce a lightweight Confident Error Regularizer to improve model calibration. Our preliminary exploration illustrates possible ways to use uncertainty estimation for selectively retaining or discarding diacritics in Arabic text with an analysis of performance in terms of correlation with diacritic error rates. For instance, the model can be used to detect words with high diacritic error rates which tend to have higher uncertainty scores at inference time. On the Tashkeela dataset, the method maintains low Diacritic Error Rate while reducing the amount of visible diacritics on the text by up to 50{\%} with thresholding-based retention."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-alblooshi-etal-2025-uncertainty">
<titleInfo>
<title>Uncertainty-driven Partial Diacritization for Arabic Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Humaid</namePart>
<namePart type="family">Ali Alblooshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Aldarmaki</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 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noidea</namePart>
<namePart type="family">Noidea</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">979-8-89176-349-4</identifier>
</relatedItem>
<abstract>We present an uncertainty-based approach to Partial Diacritization (PD) for Arabic text. We evaluate three uncertainty metrics for this task: Softmax Response, BALD via MC-dropout, and Mahalanobis Distance. We further introduce a lightweight Confident Error Regularizer to improve model calibration. Our preliminary exploration illustrates possible ways to use uncertainty estimation for selectively retaining or discarding diacritics in Arabic text with an analysis of performance in terms of correlation with diacritic error rates. For instance, the model can be used to detect words with high diacritic error rates which tend to have higher uncertainty scores at inference time. On the Tashkeela dataset, the method maintains low Diacritic Error Rate while reducing the amount of visible diacritics on the text by up to 50% with thresholding-based retention.</abstract>
<identifier type="citekey">ali-alblooshi-etal-2025-uncertainty</identifier>
<location>
<url>https://aclanthology.org/2025.uncertainlp-main.1/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty-driven Partial Diacritization for Arabic Text
%A Ali Alblooshi, Humaid
%A Shelmanov, Artem
%A Aldarmaki, Hanan
%Y Noidea, Noidea
%S Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-349-4
%F ali-alblooshi-etal-2025-uncertainty
%X We present an uncertainty-based approach to Partial Diacritization (PD) for Arabic text. We evaluate three uncertainty metrics for this task: Softmax Response, BALD via MC-dropout, and Mahalanobis Distance. We further introduce a lightweight Confident Error Regularizer to improve model calibration. Our preliminary exploration illustrates possible ways to use uncertainty estimation for selectively retaining or discarding diacritics in Arabic text with an analysis of performance in terms of correlation with diacritic error rates. For instance, the model can be used to detect words with high diacritic error rates which tend to have higher uncertainty scores at inference time. On the Tashkeela dataset, the method maintains low Diacritic Error Rate while reducing the amount of visible diacritics on the text by up to 50% with thresholding-based retention.
%U https://aclanthology.org/2025.uncertainlp-main.1/
%P 1-10
Markdown (Informal)
[Uncertainty-driven Partial Diacritization for Arabic Text](https://aclanthology.org/2025.uncertainlp-main.1/) (Ali Alblooshi et al., UncertaiNLP 2025)
ACL