@inproceedings{alzeer-akram-2026-lahja,
title = "Lahja at {D}ialect{S}ent{E}val Shared Task Subtask-1: Seed-Ensembled {MARBERT} for Multi-Dialect {A}rabic Sentiment Analysis with Zero-Shot {L}ebanese Transfer",
author = "AlZeer, Shaden Saad and
Akram, Raja Naeem",
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.184/",
pages = "1446--1451",
ISBN = "979-8-89176-497-2",
abstract = "Arabic sentiment analysis must cope with dialects that differ in vocabulary, morphology and spelling. Subtask 1 of the DialectSentEval 2026 shared task poses this problem directly: systems label hotel review sentences from five Arabic dialects as positive, negative or neutral, and one dialect (Lebanese) appears only in the test set. In this paper, we describe the Lahja submission. Since the training corpus is small (1,731 sentences) and consists of parallel translations, we treat unreliable measurement (i.e. leaky validation splits and single training runs) rather than model capacity as the main risk. We fine-tune MARBERTv2 under three random seeds, average their softmax outputs, and validate on a split grouped by review identifier so that all dialect versions of a review stay on the same side. The ensemble reached 0.790 macro-F1 on the official test set, ranking 10th of 12 teams, and lost only about two points from validation to test despite the unseen dialect. Our ablations show that the variation between seeds (about 1.5 points) exceeds the effect of orthographic normalisation or class weighting, and that the normalised ensemble, although best on validation, generalised worst on test. We therefore recommend grouped validation and seed-spread reporting as standard practice for small-data shared tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alzeer-akram-2026-lahja">
<titleInfo>
<title>Lahja at DialectSentEval Shared Task Subtask-1: Seed-Ensembled MARBERT for Multi-Dialect Arabic Sentiment Analysis with Zero-Shot Lebanese Transfer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaden</namePart>
<namePart type="given">Saad</namePart>
<namePart type="family">AlZeer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raja</namePart>
<namePart type="given">Naeem</namePart>
<namePart type="family">Akram</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>Arabic sentiment analysis must cope with dialects that differ in vocabulary, morphology and spelling. Subtask 1 of the DialectSentEval 2026 shared task poses this problem directly: systems label hotel review sentences from five Arabic dialects as positive, negative or neutral, and one dialect (Lebanese) appears only in the test set. In this paper, we describe the Lahja submission. Since the training corpus is small (1,731 sentences) and consists of parallel translations, we treat unreliable measurement (i.e. leaky validation splits and single training runs) rather than model capacity as the main risk. We fine-tune MARBERTv2 under three random seeds, average their softmax outputs, and validate on a split grouped by review identifier so that all dialect versions of a review stay on the same side. The ensemble reached 0.790 macro-F1 on the official test set, ranking 10th of 12 teams, and lost only about two points from validation to test despite the unseen dialect. Our ablations show that the variation between seeds (about 1.5 points) exceeds the effect of orthographic normalisation or class weighting, and that the normalised ensemble, although best on validation, generalised worst on test. We therefore recommend grouped validation and seed-spread reporting as standard practice for small-data shared tasks.</abstract>
<identifier type="citekey">alzeer-akram-2026-lahja</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.184/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1446</start>
<end>1451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lahja at DialectSentEval Shared Task Subtask-1: Seed-Ensembled MARBERT for Multi-Dialect Arabic Sentiment Analysis with Zero-Shot Lebanese Transfer
%A AlZeer, Shaden Saad
%A Akram, Raja Naeem
%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 alzeer-akram-2026-lahja
%X Arabic sentiment analysis must cope with dialects that differ in vocabulary, morphology and spelling. Subtask 1 of the DialectSentEval 2026 shared task poses this problem directly: systems label hotel review sentences from five Arabic dialects as positive, negative or neutral, and one dialect (Lebanese) appears only in the test set. In this paper, we describe the Lahja submission. Since the training corpus is small (1,731 sentences) and consists of parallel translations, we treat unreliable measurement (i.e. leaky validation splits and single training runs) rather than model capacity as the main risk. We fine-tune MARBERTv2 under three random seeds, average their softmax outputs, and validate on a split grouped by review identifier so that all dialect versions of a review stay on the same side. The ensemble reached 0.790 macro-F1 on the official test set, ranking 10th of 12 teams, and lost only about two points from validation to test despite the unseen dialect. Our ablations show that the variation between seeds (about 1.5 points) exceeds the effect of orthographic normalisation or class weighting, and that the normalised ensemble, although best on validation, generalised worst on test. We therefore recommend grouped validation and seed-spread reporting as standard practice for small-data shared tasks.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.184/
%P 1446-1451
Markdown (Informal)
[Lahja at DialectSentEval Shared Task Subtask-1: Seed-Ensembled MARBERT for Multi-Dialect Arabic Sentiment Analysis with Zero-Shot Lebanese Transfer](https://aclanthology.org/2026.arabicnlp-sharedtasks.184/) (AlZeer & Akram, ArabicNLP 2026)
ACL