Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXEL
This work addresses hate speech detection for low-resource languages, presenting an incremental improvement with a new attention mechanism.
The paper tackled hate speech detection in low-resource languages by developing a frozen Transformer-based architecture with a novel attention block called AXEL, achieving competitive results on English and Spanish datasets with zero-shot and few-shot learning.
Detecting hate speech, especially in low-resource languages, is a non-trivial challenge. To tackle this, we developed a tailored architecture based on frozen, pre-trained Transformers to examine cross-lingual zero-shot and few-shot learning, in addition to uni-lingual learning, on the HatEval challenge data set. With our novel attention-based classification block AXEL, we demonstrate highly competitive results on the English and Spanish subsets. We also re-sample the English subset, enabling additional, meaningful comparisons in the future.