@inproceedings{lee-2026-joshualee2,
title = "Joshualee2 at {S}em{E}val-2026 Task 9: Cross-Lingual Transformer-Based Polarization Detection",
author = "Lee, Joshua",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.347/",
pages = "2760--2764",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our system for POLAR Subtask 1 on multilingual polarization detection. The task involves binary sequence classification over 22 languages, where the model aims to predict whether a given text exhibits polarized discourse. To deal with the multilingual and resource-imbalanced nature of the dataset, we fine-tune the XLM-R, a pre-trained multilingual transformer encoder, using a language-aware sampling strategy that combines all available training data into a unified multilingual corpus. Our system achieves an overall macro-F1 of 0.781 and an average accuracy of 0.823 on the official test set. Results show strong performance in low-resource languages, though some discrepancies indicate remaining class imbalance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-2026-joshualee2">
<titleInfo>
<title>Joshualee2 at SemEval-2026 Task 9: Cross-Lingual Transformer-Based Polarization Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Lee</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>This paper describes our system for POLAR Subtask 1 on multilingual polarization detection. The task involves binary sequence classification over 22 languages, where the model aims to predict whether a given text exhibits polarized discourse. To deal with the multilingual and resource-imbalanced nature of the dataset, we fine-tune the XLM-R, a pre-trained multilingual transformer encoder, using a language-aware sampling strategy that combines all available training data into a unified multilingual corpus. Our system achieves an overall macro-F1 of 0.781 and an average accuracy of 0.823 on the official test set. Results show strong performance in low-resource languages, though some discrepancies indicate remaining class imbalance.</abstract>
<identifier type="citekey">lee-2026-joshualee2</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.347/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2760</start>
<end>2764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joshualee2 at SemEval-2026 Task 9: Cross-Lingual Transformer-Based Polarization Detection
%A Lee, Joshua
%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 lee-2026-joshualee2
%X This paper describes our system for POLAR Subtask 1 on multilingual polarization detection. The task involves binary sequence classification over 22 languages, where the model aims to predict whether a given text exhibits polarized discourse. To deal with the multilingual and resource-imbalanced nature of the dataset, we fine-tune the XLM-R, a pre-trained multilingual transformer encoder, using a language-aware sampling strategy that combines all available training data into a unified multilingual corpus. Our system achieves an overall macro-F1 of 0.781 and an average accuracy of 0.823 on the official test set. Results show strong performance in low-resource languages, though some discrepancies indicate remaining class imbalance.
%U https://aclanthology.org/2026.semeval-1.347/
%P 2760-2764
Markdown (Informal)
[Joshualee2 at SemEval-2026 Task 9: Cross-Lingual Transformer-Based Polarization Detection](https://aclanthology.org/2026.semeval-1.347/) (Lee, SemEval 2026)
ACL