<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bichi-yassine-2026-codezone">
    <titleInfo>
        <title>Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA’AKS Corpus</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abdulkadir</namePart>
        <namePart type="given">Shehu</namePart>
        <namePart type="family">Bichi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <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>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
        </titleInfo>
        <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">Mo</namePart>
            <namePart type="family">El-Haj</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Ezzini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Abstract We launched ASBN-MT5, the system for Arabic Sentiment Swap, which performs the task of inverting the sentiment of a sentence while keeping the meaning intact. This is a sequence-to-sequence task. We demonstrate ASBN-MT5: mT5, which is a MultiLingual T5 model, fine-tuned on the provided dataset of the AraSentEval 2026 Shared Task. We describe the data as the first of its kind for the Arabic language, as MAAKS is the first manually composed, parallel, cross-linguistic corpus for the Arabic language. With the preliminary results of Sentiment Flip for the task of Sentiment Inversion, we have recorded a rate of 59.5% for positive to negative conversions and 58.5% for negative to positive conversions, while maintaining an average similarity to the original sentences of 0.955. We present the Arabic prompts and a neuro-developmental (Deep Learning) recipe. Due to the evaluation criteria which include Exact Match, Flip Success, Surface Similarity, and Quality of Output, we restrict the use of Prepended Negation as the main technique and recommend the use of LLMs designed for the Arabic language in the near future. Keywords: mT5, sequence-to-sequence, AraSentEval 2026, Arabic NLP, Text Style Transfer, Sentiment Swap</abstract>
    <identifier type="citekey">bichi-yassine-2026-codezone</identifier>
    <identifier type="doi">10.63317/2qp7m87fbeti</identifier>
    <location>
        <url>https://aclanthology.org/2026.osact-1.40/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>288</start>
            <end>291</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA’AKS Corpus
%A Bichi, Abdulkadir Shehu
%A Yassine, Sarah
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F bichi-yassine-2026-codezone
%X Abstract We launched ASBN-MT5, the system for Arabic Sentiment Swap, which performs the task of inverting the sentiment of a sentence while keeping the meaning intact. This is a sequence-to-sequence task. We demonstrate ASBN-MT5: mT5, which is a MultiLingual T5 model, fine-tuned on the provided dataset of the AraSentEval 2026 Shared Task. We describe the data as the first of its kind for the Arabic language, as MAAKS is the first manually composed, parallel, cross-linguistic corpus for the Arabic language. With the preliminary results of Sentiment Flip for the task of Sentiment Inversion, we have recorded a rate of 59.5% for positive to negative conversions and 58.5% for negative to positive conversions, while maintaining an average similarity to the original sentences of 0.955. We present the Arabic prompts and a neuro-developmental (Deep Learning) recipe. Due to the evaluation criteria which include Exact Match, Flip Success, Surface Similarity, and Quality of Output, we restrict the use of Prepended Negation as the main technique and recommend the use of LLMs designed for the Arabic language in the near future. Keywords: mT5, sequence-to-sequence, AraSentEval 2026, Arabic NLP, Text Style Transfer, Sentiment Swap
%R 10.63317/2qp7m87fbeti
%U https://aclanthology.org/2026.osact-1.40/
%U https://doi.org/10.63317/2qp7m87fbeti
%P 288-291

Markdown (Informal)

[Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA’AKS Corpus](https://aclanthology.org/2026.osact-1.40/) (Bichi & Yassine, OSACT 2026)

• Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA’AKS Corpus (Bichi & Yassine, OSACT 2026)

ACL

• Abdulkadir Shehu Bichi and Sarah Yassine. 2026. Codezone Research Group at AraSentEval Shared Task: Arabic Sentiment Swap beyond Negation Prepending, Benchmarking Multilingual T5 against Large Language Models on the MA’AKS Corpus. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 288–291, Palma, Mallorca (Spain). Association for Computational Linguistics.