This paper uses a fine-tuned TwHIN-BERT model, a multilingual encoder-based transformer pre-trained on social media data, to classify text across five polarization categories, suggesting that performance in such a multi-label polarization detection task is more strongly driven by local distributional properties than by resource size.
This approach combines option-permutation augmentation for Chinese data, annotator vote expansion for Indonesian data, and binary reformulation with SinhalaMMLU augmentation with SinhalaMMLU augmentation for Sri Lankan data to focus on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka.
This work examines the effectiveness of stacking traditional machine learning techniques like Logistic Regression, k-Nearest Neighbors, Random Forest, Multi-Layer Perceptron, Support Vector Classifier and simple word counting and compares them to BERT, a powerful pre-trained language model.
Björn Kießwetter, Christoph Lukas, Tim Sieber· 0 citations
This paper utilized a pre-trained DeBERTa-V3 backbone to capture semantic meaning through disentangled attention to capture semantic meaning through disentangled attention, and proposed a Hybrid MSE-CCC Loss to identify distributional relationships that simple regression missed.
