@inproceedings{fuganti-etal-2026-umusp,
title = "{UMUSP} at {S}em{E}val-2026 Task 9: Mitigating Cross-Lingual Interference via Selective Multilingual and Multitask Specialization",
author = "Fuganti, Julio Cesar and
Ferreira Leite Da Silva, Tulio and
Gala, Adelino and
S. Marcondes, Francisco and
Machado, Jos{\'e} and
Novais, Paulo",
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-1.401/",
pages = "3199--3208",
ISBN = "979-8-89176-414-9",
abstract = "This paper proposes a selective multilingual and multitask fine-tuning strategy for online polarization detection that improves cross-lingual stability over fully joint training. Covering all three subtasks {---} polarization detection (POLARDETECT), polarization type classification (POLARTYPE), and rhetorical manifestation identification (POLARMANIFEST) {---} across all 22 languages of the shared task, the approach introduces controlled specialization, where languages and subtasks are grouped empirically and separate specialist models are fine-tuned for each subset. Restricting parameter sharing substantially improves performance even without ensemble averaging, whereas ensembling jointly trained models fails to mitigate instability. The final specialist ensemble improves Task 3 macro-F1 from 0.3330 to 0.4920 and reduces cross-lingual dispersion (CV: 0.613 {\textrightarrow} 0.321). Under the official ranking framework, the system ranks 7th among 16 submissions with complete multilingual and multitask coverage and remains within 5{\%} of the best system in 37.70{\%} of evaluation conditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fuganti-etal-2026-umusp">
<titleInfo>
<title>UMUSP at SemEval-2026 Task 9: Mitigating Cross-Lingual Interference via Selective Multilingual and Multitask Specialization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julio</namePart>
<namePart type="given">Cesar</namePart>
<namePart type="family">Fuganti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tulio</namePart>
<namePart type="family">Ferreira Leite Da Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adelino</namePart>
<namePart type="family">Gala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">S. Marcondes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Machado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulo</namePart>
<namePart type="family">Novais</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 proposes a selective multilingual and multitask fine-tuning strategy for online polarization detection that improves cross-lingual stability over fully joint training. Covering all three subtasks — polarization detection (POLARDETECT), polarization type classification (POLARTYPE), and rhetorical manifestation identification (POLARMANIFEST) — across all 22 languages of the shared task, the approach introduces controlled specialization, where languages and subtasks are grouped empirically and separate specialist models are fine-tuned for each subset. Restricting parameter sharing substantially improves performance even without ensemble averaging, whereas ensembling jointly trained models fails to mitigate instability. The final specialist ensemble improves Task 3 macro-F1 from 0.3330 to 0.4920 and reduces cross-lingual dispersion (CV: 0.613 → 0.321). Under the official ranking framework, the system ranks 7th among 16 submissions with complete multilingual and multitask coverage and remains within 5% of the best system in 37.70% of evaluation conditions.</abstract>
<identifier type="citekey">fuganti-etal-2026-umusp</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.401/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3199</start>
<end>3208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMUSP at SemEval-2026 Task 9: Mitigating Cross-Lingual Interference via Selective Multilingual and Multitask Specialization
%A Fuganti, Julio Cesar
%A Ferreira Leite Da Silva, Tulio
%A Gala, Adelino
%A S. Marcondes, Francisco
%A Machado, José
%A Novais, Paulo
%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 fuganti-etal-2026-umusp
%X This paper proposes a selective multilingual and multitask fine-tuning strategy for online polarization detection that improves cross-lingual stability over fully joint training. Covering all three subtasks — polarization detection (POLARDETECT), polarization type classification (POLARTYPE), and rhetorical manifestation identification (POLARMANIFEST) — across all 22 languages of the shared task, the approach introduces controlled specialization, where languages and subtasks are grouped empirically and separate specialist models are fine-tuned for each subset. Restricting parameter sharing substantially improves performance even without ensemble averaging, whereas ensembling jointly trained models fails to mitigate instability. The final specialist ensemble improves Task 3 macro-F1 from 0.3330 to 0.4920 and reduces cross-lingual dispersion (CV: 0.613 → 0.321). Under the official ranking framework, the system ranks 7th among 16 submissions with complete multilingual and multitask coverage and remains within 5% of the best system in 37.70% of evaluation conditions.
%U https://aclanthology.org/2026.semeval-1.401/
%P 3199-3208
Markdown (Informal)
[UMUSP at SemEval-2026 Task 9: Mitigating Cross-Lingual Interference via Selective Multilingual and Multitask Specialization](https://aclanthology.org/2026.semeval-1.401/) (Fuganti et al., SemEval 2026)
ACL