@inproceedings{ibrahim-etal-2026-alexis-dialectsenteval-subtask,
title = "{ALEXIS} at {D}ialect{S}ent{E}val Subtask 2 Retrieval-Augmented, Preference-Tuned Generation for {A}rabic Sentiment Swap",
author = "Ibrahim, Momen and
Hassib, Mariam E. and
Mahmoud Salem, Ahmed and
Torki, Marwan",
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.188/",
pages = "1467--1472",
ISBN = "979-8-89176-497-2",
abstract = "Sentiment swap is the task of rewriting a sentence so that it carries the opposite polarity while its topic stays the same. We present a system for Arabic sentiment swap built on two observations about the data. First, the swap is a local edit rather than a paraphrase: 91{\%} of reference rewrites stay within two words of their source. Second, the polarity to swap away from has to be predicted, because the test data does not provide it. We therefore fine-tune mT5 and refine it with Direct Preference Optimization under a reward that balances target-polarity probability against content preservation. At inference we pool candidates from four generators, one of them a minimal-edit tagger, together with a retrieval index, rerank them with the same balance, and repair them with polarity-flip lexicons mined from the training set. Source polarity is supplied by a dedicated classifier that reaches 97.3{\%} accuracy, against 74.3{\%} for the off-the-shelf sentiment model that the evaluation itself uses. Every component was scored on the official leaderboard: generation-side work contributes $+0.044$ Sentiment Style Accuracy, and the dedicated polarity classifier a further $+0.155$. The final system reaches 0.9581 Sentiment Style Accuracy, 56.91 BLEU and 72.18 chrF, ranking 1st of 15 submissions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibrahim-etal-2026-alexis-dialectsenteval-subtask">
<titleInfo>
<title>ALEXIS at DialectSentEval Subtask 2 Retrieval-Augmented, Preference-Tuned Generation for Arabic Sentiment Swap</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momen</namePart>
<namePart type="family">Ibrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Hassib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Mahmoud Salem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Torki</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>Sentiment swap is the task of rewriting a sentence so that it carries the opposite polarity while its topic stays the same. We present a system for Arabic sentiment swap built on two observations about the data. First, the swap is a local edit rather than a paraphrase: 91% of reference rewrites stay within two words of their source. Second, the polarity to swap away from has to be predicted, because the test data does not provide it. We therefore fine-tune mT5 and refine it with Direct Preference Optimization under a reward that balances target-polarity probability against content preservation. At inference we pool candidates from four generators, one of them a minimal-edit tagger, together with a retrieval index, rerank them with the same balance, and repair them with polarity-flip lexicons mined from the training set. Source polarity is supplied by a dedicated classifier that reaches 97.3% accuracy, against 74.3% for the off-the-shelf sentiment model that the evaluation itself uses. Every component was scored on the official leaderboard: generation-side work contributes +0.044 Sentiment Style Accuracy, and the dedicated polarity classifier a further +0.155. The final system reaches 0.9581 Sentiment Style Accuracy, 56.91 BLEU and 72.18 chrF, ranking 1st of 15 submissions.</abstract>
<identifier type="citekey">ibrahim-etal-2026-alexis-dialectsenteval-subtask</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.188/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1467</start>
<end>1472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T ALEXIS at DialectSentEval Subtask 2 Retrieval-Augmented, Preference-Tuned Generation for Arabic Sentiment Swap %A Ibrahim, Momen %A Hassib, Mariam E. %A Mahmoud Salem, Ahmed %A Torki, Marwan %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 ibrahim-etal-2026-alexis-dialectsenteval-subtask %X Sentiment swap is the task of rewriting a sentence so that it carries the opposite polarity while its topic stays the same. We present a system for Arabic sentiment swap built on two observations about the data. First, the swap is a local edit rather than a paraphrase: 91% of reference rewrites stay within two words of their source. Second, the polarity to swap away from has to be predicted, because the test data does not provide it. We therefore fine-tune mT5 and refine it with Direct Preference Optimization under a reward that balances target-polarity probability against content preservation. At inference we pool candidates from four generators, one of them a minimal-edit tagger, together with a retrieval index, rerank them with the same balance, and repair them with polarity-flip lexicons mined from the training set. Source polarity is supplied by a dedicated classifier that reaches 97.3% accuracy, against 74.3% for the off-the-shelf sentiment model that the evaluation itself uses. Every component was scored on the official leaderboard: generation-side work contributes +0.044 Sentiment Style Accuracy, and the dedicated polarity classifier a further +0.155. The final system reaches 0.9581 Sentiment Style Accuracy, 56.91 BLEU and 72.18 chrF, ranking 1st of 15 submissions. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.188/ %P 1467-1472
Markdown (Informal)
[ALEXIS at DialectSentEval Subtask 2 Retrieval-Augmented, Preference-Tuned Generation for Arabic Sentiment Swap](https://aclanthology.org/2026.arabicnlp-sharedtasks.188/) (Ibrahim et al., ArabicNLP 2026)