@inproceedings{francies-etal-2026-reglat,
title = "{REGLAT} at {A}lexandria{X}-2026: A Two-Stage Multi-Encoder Framework for Character-Level Error Detection and {LQM} Classification in Dialectal {A}rabic Machine Translation",
author = "Francies, Mariam and
Ramzy, Bakhom and
Ashraf, Nsrin and
Fetouh, Ahmed M. and
Nayel, Hamada",
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.105/",
pages = "842--847",
ISBN = "979-8-89176-497-2",
abstract = "We describe REGLAT{'}s submission to AlexandriaX-2026 Subtask 3, which requires character-offset error spans in dialectal Arabic machine translations and a Linguistically Motivated Multidimensional Quality Metrics (LQM) category for each span. The system separates localization from classification. Four CAMeLBERT-DA and MARBERTv2 BIO taggers project token probabilities to a shared character grid; whitespace-segment probabilities are then thresholded, bridged, and optionally dilated. A second four-member ensemble classifies detected spans using the marked hypothesis, English source, and translation direction, with class weighting and fitted logit biases. REGLAT ranked fourth out of six teams with an official Overall Score of 0.4021 (Overlap F1 0.4272; Error-Class score 0.3770). Its Exact Match F1 of 0.0041 exposes severe boundary imprecision. We document a scorer mismatch in development-time selection and therefore treat earlier development values as proxy-metric results, not official-metric estimates."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="francies-etal-2026-reglat">
<titleInfo>
<title>REGLAT at AlexandriaX-2026: A Two-Stage Multi-Encoder Framework for Character-Level Error Detection and LQM Classification in Dialectal Arabic Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Francies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bakhom</namePart>
<namePart type="family">Ramzy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nsrin</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Fetouh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamada</namePart>
<namePart type="family">Nayel</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>We describe REGLAT’s submission to AlexandriaX-2026 Subtask 3, which requires character-offset error spans in dialectal Arabic machine translations and a Linguistically Motivated Multidimensional Quality Metrics (LQM) category for each span. The system separates localization from classification. Four CAMeLBERT-DA and MARBERTv2 BIO taggers project token probabilities to a shared character grid; whitespace-segment probabilities are then thresholded, bridged, and optionally dilated. A second four-member ensemble classifies detected spans using the marked hypothesis, English source, and translation direction, with class weighting and fitted logit biases. REGLAT ranked fourth out of six teams with an official Overall Score of 0.4021 (Overlap F1 0.4272; Error-Class score 0.3770). Its Exact Match F1 of 0.0041 exposes severe boundary imprecision. We document a scorer mismatch in development-time selection and therefore treat earlier development values as proxy-metric results, not official-metric estimates.</abstract>
<identifier type="citekey">francies-etal-2026-reglat</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.105/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>842</start>
<end>847</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REGLAT at AlexandriaX-2026: A Two-Stage Multi-Encoder Framework for Character-Level Error Detection and LQM Classification in Dialectal Arabic Machine Translation
%A Francies, Mariam
%A Ramzy, Bakhom
%A Ashraf, Nsrin
%A Fetouh, Ahmed M.
%A Nayel, Hamada
%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 francies-etal-2026-reglat
%X We describe REGLAT’s submission to AlexandriaX-2026 Subtask 3, which requires character-offset error spans in dialectal Arabic machine translations and a Linguistically Motivated Multidimensional Quality Metrics (LQM) category for each span. The system separates localization from classification. Four CAMeLBERT-DA and MARBERTv2 BIO taggers project token probabilities to a shared character grid; whitespace-segment probabilities are then thresholded, bridged, and optionally dilated. A second four-member ensemble classifies detected spans using the marked hypothesis, English source, and translation direction, with class weighting and fitted logit biases. REGLAT ranked fourth out of six teams with an official Overall Score of 0.4021 (Overlap F1 0.4272; Error-Class score 0.3770). Its Exact Match F1 of 0.0041 exposes severe boundary imprecision. We document a scorer mismatch in development-time selection and therefore treat earlier development values as proxy-metric results, not official-metric estimates.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.105/
%P 842-847
Markdown (Informal)
[REGLAT at AlexandriaX-2026: A Two-Stage Multi-Encoder Framework for Character-Level Error Detection and LQM Classification in Dialectal Arabic Machine Translation](https://aclanthology.org/2026.arabicnlp-sharedtasks.105/) (Francies et al., ArabicNLP 2026)
ACL