PingAn-NLP at SemEval-2026 Task 9: Multi-Stage Alignment via GRPO and Tiered Ensemble Voting for Multilingual Polarization Detection

Sahara Tokenizers at MWE-2026 PARSEME 2.0 Subtask 1: Combining Contextual Embeddings with Structural Decoding for Multi-Word Expression Detection

Alation studies reveal a strong synergy between POS features and CRF decoding, with the combined approach yielding the best single-model performance, and ensembling models trained with different objectives improves both overall F1 score and discontinuous MWE scores, demonstrating the importance of training diversity for capturing non-adjacent syntactic patterns.

ILA-POLAR at SemEval-2026 Task 9: Multi-label Polarization Classification with TwHIN-BERT and SCUT Threshold Optimization

Ensemble-Based Approach for Amazigh POS Tagging: Leveraging Multiple Models for Enhanced Performance in Low-Resource Language Processing

The results show that hybrid ensemble methods can improve token-level accuracy in low-resource POS tagging, while also revealing a trade-off between frequent-tag accuracy and rare-tag robustness.

UIT-Polar at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization

HausaNLP at SemEval-2026 Task 7: A Locale-Conditional, Multi-Model Prompting Pipeline for Hausa Cultural Question Answering

Error analysis shows that a non-trivial fraction of failures are placeholder strings caused by API errors rather than incorrect generations, and that surface-level mismatches (verbosity, ortho-graphic variation) account for many of the remaining errors.

NERBench-Chhattisgarh: A Multi-Family NER Dataset for Low-Resource Indic Languages

A morphological barrier is shown: while pivot-based adaptation facilitates transfer for distant languages through script alignment, it induces negative transfer in morphologically complex agglutinative languages like Gondi.