@inproceedings{yassine-2026-arabicmtdiagnostics,
title = "{A}rabic{MTD}iagnostics at {A}lexandria{X}-2026: Detecting and Classifying Errors in Dialectal {A}rabic Machine Translation Outputs",
author = "Yassine, Sarah",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.103/",
pages = "827--833",
ISBN = "979-8-89176-497-2",
abstract = "Dialectal Arabic MT error detection asks a sys tem to locate error spans in a machine trans lation and label each with a linguistic error category. It is hard because the dialects lack a standardised orthography and the error cate gories are severely imbalanced. In Subtask 3 of the AlexandriaX 2026 shared task, the in put is an English sentence and its machine translation into one of five Arabic dialects, and the output is character-level error spans with their LQM categories. The central difficulty is collapse onto the majority sociolinguistics class, 58{\%} of training spans, leaving rare cat egories undetected. To address this, we fine tune NileChat-3B-Base with QLoRA on a sin gle 8 GB consumer GPU, casting the task as schema-prompted JSON generation and com bining character-position annotations that let the model copy offsets rather than count them, a category guide with one worked example per error type, and self-consistency decoding merging five samples by character-level union voting. Our system scores 0.3484 Overall on the official test set. We report two negative results: early stopping on validation loss de grades performance, since rare categories are acquired only in later epochs, and fine-tuning on the skewed distribution lowers macro-F1 be low the un-fine-tuned baseline until the cate gory guide is added"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yassine-2026-arabicmtdiagnostics">
<titleInfo>
<title>ArabicMTDiagnostics at AlexandriaX-2026: Detecting and Classifying Errors in Dialectal Arabic Machine Translation Outputs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Yassine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Dialectal Arabic MT error detection asks a sys tem to locate error spans in a machine trans lation and label each with a linguistic error category. It is hard because the dialects lack a standardised orthography and the error cate gories are severely imbalanced. In Subtask 3 of the AlexandriaX 2026 shared task, the in put is an English sentence and its machine translation into one of five Arabic dialects, and the output is character-level error spans with their LQM categories. The central difficulty is collapse onto the majority sociolinguistics class, 58% of training spans, leaving rare cat egories undetected. To address this, we fine tune NileChat-3B-Base with QLoRA on a sin gle 8 GB consumer GPU, casting the task as schema-prompted JSON generation and com bining character-position annotations that let the model copy offsets rather than count them, a category guide with one worked example per error type, and self-consistency decoding merging five samples by character-level union voting. Our system scores 0.3484 Overall on the official test set. We report two negative results: early stopping on validation loss de grades performance, since rare categories are acquired only in later epochs, and fine-tuning on the skewed distribution lowers macro-F1 be low the un-fine-tuned baseline until the cate gory guide is added</abstract>
<identifier type="citekey">yassine-2026-arabicmtdiagnostics</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.103/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>827</start>
<end>833</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArabicMTDiagnostics at AlexandriaX-2026: Detecting and Classifying Errors in Dialectal Arabic Machine Translation Outputs
%A Yassine, Sarah
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F yassine-2026-arabicmtdiagnostics
%X Dialectal Arabic MT error detection asks a sys tem to locate error spans in a machine trans lation and label each with a linguistic error category. It is hard because the dialects lack a standardised orthography and the error cate gories are severely imbalanced. In Subtask 3 of the AlexandriaX 2026 shared task, the in put is an English sentence and its machine translation into one of five Arabic dialects, and the output is character-level error spans with their LQM categories. The central difficulty is collapse onto the majority sociolinguistics class, 58% of training spans, leaving rare cat egories undetected. To address this, we fine tune NileChat-3B-Base with QLoRA on a sin gle 8 GB consumer GPU, casting the task as schema-prompted JSON generation and com bining character-position annotations that let the model copy offsets rather than count them, a category guide with one worked example per error type, and self-consistency decoding merging five samples by character-level union voting. Our system scores 0.3484 Overall on the official test set. We report two negative results: early stopping on validation loss de grades performance, since rare categories are acquired only in later epochs, and fine-tuning on the skewed distribution lowers macro-F1 be low the un-fine-tuned baseline until the cate gory guide is added
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.103/
%P 827-833
Markdown (Informal)
[ArabicMTDiagnostics at AlexandriaX-2026: Detecting and Classifying Errors in Dialectal Arabic Machine Translation Outputs](https://aclanthology.org/2026.arabicnlp-sharedtasks.103/) (Yassine, ArabicNLP 2026)
ACL