@inproceedings{dash-etal-2026-semantic,
title = "Semantic Vectors at {S}em{E}val-2026 Task 9: Robust Multilingual Polarization Detection via Dual-Encoder Fusion and Expert Ensembling",
author = "Dash, Ankit and
Mittal, Priyanshu and
Prashant, Piyush and
Saumya, Sunil",
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-1.239/",
pages = "1903--1910",
ISBN = "979-8-89176-414-9",
abstract = "We present SEMANTIC VECTORS, our system for POLAR@SemEval-2026 Task 9 on multilingual online polarization detection across 22 typologically diverse languages. Polarization is frequently conveyed through implicit rhetorical framing, making cross-lingual detection highly challenging. We address this with a Siamese dual-encoder jointly fine-tuning mDeBERTa-v3-base and XLM-ROBERTa-large via 4-bit QLoRA, fused with language-specific expert models (GBERT, Italian BERT, Swahili BERT) through an XGBoost meta-stacker with per-language Platt calibration. Rather than addressing class imbalance, focal loss functions as a hard-example miner, concentrating gradients on subtly framed instances rather than lexically obvious ones. Combined with per-language threshold optimization, our system achieves macro-F1=0.797 and accuracy=0.827 across all 22 languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dash-etal-2026-semantic">
<titleInfo>
<title>Semantic Vectors at SemEval-2026 Task 9: Robust Multilingual Polarization Detection via Dual-Encoder Fusion and Expert Ensembling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanshu</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Prashant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Saumya</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 SEMANTIC VECTORS, our system for POLAR@SemEval-2026 Task 9 on multilingual online polarization detection across 22 typologically diverse languages. Polarization is frequently conveyed through implicit rhetorical framing, making cross-lingual detection highly challenging. We address this with a Siamese dual-encoder jointly fine-tuning mDeBERTa-v3-base and XLM-ROBERTa-large via 4-bit QLoRA, fused with language-specific expert models (GBERT, Italian BERT, Swahili BERT) through an XGBoost meta-stacker with per-language Platt calibration. Rather than addressing class imbalance, focal loss functions as a hard-example miner, concentrating gradients on subtly framed instances rather than lexically obvious ones. Combined with per-language threshold optimization, our system achieves macro-F1=0.797 and accuracy=0.827 across all 22 languages.</abstract>
<identifier type="citekey">dash-etal-2026-semantic</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.239/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1903</start>
<end>1910</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Vectors at SemEval-2026 Task 9: Robust Multilingual Polarization Detection via Dual-Encoder Fusion and Expert Ensembling
%A Dash, Ankit
%A Mittal, Priyanshu
%A Prashant, Piyush
%A Saumya, Sunil
%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 dash-etal-2026-semantic
%X We present SEMANTIC VECTORS, our system for POLAR@SemEval-2026 Task 9 on multilingual online polarization detection across 22 typologically diverse languages. Polarization is frequently conveyed through implicit rhetorical framing, making cross-lingual detection highly challenging. We address this with a Siamese dual-encoder jointly fine-tuning mDeBERTa-v3-base and XLM-ROBERTa-large via 4-bit QLoRA, fused with language-specific expert models (GBERT, Italian BERT, Swahili BERT) through an XGBoost meta-stacker with per-language Platt calibration. Rather than addressing class imbalance, focal loss functions as a hard-example miner, concentrating gradients on subtly framed instances rather than lexically obvious ones. Combined with per-language threshold optimization, our system achieves macro-F1=0.797 and accuracy=0.827 across all 22 languages.
%U https://aclanthology.org/2026.semeval-1.239/
%P 1903-1910
Markdown (Informal)
[Semantic Vectors at SemEval-2026 Task 9: Robust Multilingual Polarization Detection via Dual-Encoder Fusion and Expert Ensembling](https://aclanthology.org/2026.semeval-1.239/) (Dash et al., SemEval 2026)
ACL