<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dahl-etal-2026-tralaleros">
    <titleInfo>
        <title>Tralaleros at SemEval-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adrian</namePart>
        <namePart type="family">Dahl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bado</namePart>
        <namePart type="family">Völckers</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Mierzwa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>We present a multilingual polarization detection system for SemEval-2026 Task 9 (Subtask 1), covering 22 languages with transformer-based models. We evaluate four strategies: data rebalancing, hyperparameter optimization, model scaling, and ensembling, and show that undersampling harms performance, while larger pretrained models improve results substantially. Our best single model, XLM-RoBERTa Large, achieves a Macro-F1 of 0.7929, with analysis showing complementary strengths across model families (e.g., RemBERT for several Indic languages and mDeBERTa for Semitic/morphologically rich languages). Ensemble gains are marginal, suggesting language-aware routing is more promising than uniform aggregation. We also provide a privacy-preserving Firefox extension that runs local ONNX inference for practical deployment without sending user text to external servers.</abstract>
    <identifier type="citekey">dahl-etal-2026-tralaleros</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.51/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>343</start>
            <end>353</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tralaleros at SemEval-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models
%A Dahl, Adrian
%A Völckers, Bado
%A Mierzwa, Adam
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F dahl-etal-2026-tralaleros
%X We present a multilingual polarization detection system for SemEval-2026 Task 9 (Subtask 1), covering 22 languages with transformer-based models. We evaluate four strategies: data rebalancing, hyperparameter optimization, model scaling, and ensembling, and show that undersampling harms performance, while larger pretrained models improve results substantially. Our best single model, XLM-RoBERTa Large, achieves a Macro-F1 of 0.7929, with analysis showing complementary strengths across model families (e.g., RemBERT for several Indic languages and mDeBERTa for Semitic/morphologically rich languages). Ensemble gains are marginal, suggesting language-aware routing is more promising than uniform aggregation. We also provide a privacy-preserving Firefox extension that runs local ONNX inference for practical deployment without sending user text to external servers.
%U https://aclanthology.org/2026.semeval-1.51/
%P 343-353

Markdown (Informal)

[Tralaleros at SemEval-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models](https://aclanthology.org/2026.semeval-1.51/) (Dahl et al., SemEval 2026)

• Tralaleros at SemEval-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models (Dahl et al., SemEval 2026)

ACL

• Adrian Dahl, Bado Völckers, and Adam Mierzwa. 2026. Tralaleros at SemEval-2026 Task 9: Multilingual Polarization Detection with Transformer-based Models. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 343–353, San Diego, California, USA. Association for Computational Linguistics.