Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings
This paper describes my submission to the Polarization Shared Task at SemEval-2025, which addresses polarization detection and classification in social media text. I develop Transformer-based systems for English and Swahili across three subtasks: binary polarization detection, multi-label target type classification, and multi-label manifestation identification. The approach leverages multilingual and African language-specialized models (mDeBERTa-v3-base, SwahBERT, AfriBERTa-large), class-weighted loss functions, iterative stratified data splitting, and per-label threshold tuning to handle severe class imbalance. The best configuration, mDeBERTa-v3-base, achieves 0.8032 macro-F1 on validation for binary detection, with competitive performance on multi-label tasks (up to 0.556 macro-F1). Error analysis reveals persistent challenges with implicit polarization, code-switching, and distinguishing heated political discourse from genuine polarization.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Finite sample guarantees for quantile estimation: An application to detector threshold tuning
In threshold-based anomaly detection, we want to tune the threshold of a detector to achieve an acceptable false alarm rate. However, tuning the threshold is often a non-trivial task due to unknown detector output distri…
Anomaly DetectionSugeno integral generalization applied to improve adaptive image binarization
Classic adaptive binarization methodologies threshold pixels intensity with re-spect to adjacent pixels exploiting integral images. In turn, integral imagesare generally computed optimally by using the summed-area-table …
BinarizationMultilingual Translation with Extensible Multilingual Pretraining and Finetuning
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages. Previous work in multilingual pretraining has demonstrated that machine …
Machine TranslationTranslationTowards Threshold Invariant Fair Classification
Effective machine learning models can automatically learn useful information from a large quantity of data and provide decisions in a high accuracy. These models may, however, lead to unfair predictions in certain sense …
BIG-bench Machine LearningClassificationFairnessGeneral ClassificationDomain-Specific Japanese ELECTRA Model Using a Small Corpus
Recently, domain shift, which affects accuracy due to differences in data between source and target domains, has become a serious issue when using machine learning methods to solve natural language processing tasks. With…
ArticlesComputational EfficiencyDocument ClassificationLanguage Modeling+2