YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911663904522240 |
|---|---|
| author | Guo, Fengze Chang, Yue |
| author_facet | Guo, Fengze Chang, Yue |
| contents | This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detection, target classification, and manifestation identification. We propose a heterogeneous ensemble of multilingual pretrained models, combining XLM-RoBERTa-large and mDeBERTa-v3-base. We investigate techniques such as multi-task learning, translation-based data augmentation, and class weighting to improve classification performance under severe label imbalance. Our findings indicate that independent task modeling combined with class weighting is more effective. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06231 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling Guo, Fengze Chang, Yue Computation and Language This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detection, target classification, and manifestation identification. We propose a heterogeneous ensemble of multilingual pretrained models, combining XLM-RoBERTa-large and mDeBERTa-v3-base. We investigate techniques such as multi-task learning, translation-based data augmentation, and class weighting to improve classification performance under severe label imbalance. Our findings indicate that independent task modeling combined with class weighting is more effective. |
| title | YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.06231 |