@inproceedings{le-phung-2026-alphalyrae,
title = "{A}lpha{L}yrae at {S}em{E}val-2026 Task 9: Metric Learning and Asymmetric Loss for {C}hinese Polarization Analysis",
author = "Le, Minh-Hoang and
Phung, Khoan",
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-1.72/",
pages = "503--508",
ISBN = "979-8-89176-414-9",
abstract = "For the Chinese track of SemEval-2026 Task 9 (Detecting Online Polarization), we address two key challenges: polarized content frequently uses implicit language (e.g., homophones and coded terms) to evade moderation, and class distributions exhibit severe long-tail imbalance. We propose a metric learning approach that frames polarization detection as semantic similarity matching, which captures implicit language patterns better than linear decision boundaries. We fine-tune an ERNIE-3.0 encoder with SoftTriple loss and apply ik/iNN retrieval for binary detection (Subtask 1). For multi-label categorization (Subtasks 2 and 3), we transfer learned representations from the detection model and fine-tune with Asymmetric Loss. A priority-based stratified cross-validation strategy ensures minority classes appear across all training folds despite extreme label skew. Evaluated on the official 1,927-sample test set using an end-to-end pipeline, our system achieved Macro-F1 scores of 0.9190 (Rank 6) on Polarization Detection, 0.8244 (Rank 5) on Type Classification, and 0.6670 (Rank 4) on Manifestation Identification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-phung-2026-alphalyrae">
<titleInfo>
<title>AlphaLyrae at SemEval-2026 Task 9: Metric Learning and Asymmetric Loss for Chinese Polarization Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh-Hoang</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoan</namePart>
<namePart type="family">Phung</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>For the Chinese track of SemEval-2026 Task 9 (Detecting Online Polarization), we address two key challenges: polarized content frequently uses implicit language (e.g., homophones and coded terms) to evade moderation, and class distributions exhibit severe long-tail imbalance. We propose a metric learning approach that frames polarization detection as semantic similarity matching, which captures implicit language patterns better than linear decision boundaries. We fine-tune an ERNIE-3.0 encoder with SoftTriple loss and apply ik/iNN retrieval for binary detection (Subtask 1). For multi-label categorization (Subtasks 2 and 3), we transfer learned representations from the detection model and fine-tune with Asymmetric Loss. A priority-based stratified cross-validation strategy ensures minority classes appear across all training folds despite extreme label skew. Evaluated on the official 1,927-sample test set using an end-to-end pipeline, our system achieved Macro-F1 scores of 0.9190 (Rank 6) on Polarization Detection, 0.8244 (Rank 5) on Type Classification, and 0.6670 (Rank 4) on Manifestation Identification.</abstract>
<identifier type="citekey">le-phung-2026-alphalyrae</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.72/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>503</start>
<end>508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaLyrae at SemEval-2026 Task 9: Metric Learning and Asymmetric Loss for Chinese Polarization Analysis
%A Le, Minh-Hoang
%A Phung, Khoan
%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 le-phung-2026-alphalyrae
%X For the Chinese track of SemEval-2026 Task 9 (Detecting Online Polarization), we address two key challenges: polarized content frequently uses implicit language (e.g., homophones and coded terms) to evade moderation, and class distributions exhibit severe long-tail imbalance. We propose a metric learning approach that frames polarization detection as semantic similarity matching, which captures implicit language patterns better than linear decision boundaries. We fine-tune an ERNIE-3.0 encoder with SoftTriple loss and apply ik/iNN retrieval for binary detection (Subtask 1). For multi-label categorization (Subtasks 2 and 3), we transfer learned representations from the detection model and fine-tune with Asymmetric Loss. A priority-based stratified cross-validation strategy ensures minority classes appear across all training folds despite extreme label skew. Evaluated on the official 1,927-sample test set using an end-to-end pipeline, our system achieved Macro-F1 scores of 0.9190 (Rank 6) on Polarization Detection, 0.8244 (Rank 5) on Type Classification, and 0.6670 (Rank 4) on Manifestation Identification.
%U https://aclanthology.org/2026.semeval-1.72/
%P 503-508
Markdown (Informal)
[AlphaLyrae at SemEval-2026 Task 9: Metric Learning and Asymmetric Loss for Chinese Polarization Analysis](https://aclanthology.org/2026.semeval-1.72/) (Le & Phung, SemEval 2026)
ACL