Mitigating Data Imbalance in Automated Speaking Assessment
This addresses biased predictions in automated speaking assessment for second-language learners, representing an incremental improvement.
The paper tackled class imbalance in automated speaking assessment models by introducing the Balancing Logit Variation (BLV) loss, which improved classification accuracy and fairness on the ICNALE benchmark dataset.
Automated Speaking Assessment (ASA) plays a crucial role in evaluating second-language (L2) learners proficiency. However, ASA models often suffer from class imbalance, leading to biased predictions. To address this, we introduce a novel objective for training ASA models, dubbed the Balancing Logit Variation (BLV) loss, which perturbs model predictions to improve feature representation for minority classes without modifying the dataset. Evaluations on the ICNALE benchmark dataset show that integrating the BLV loss into a celebrated text-based (BERT) model significantly enhances classification accuracy and fairness, making automated speech evaluation more robust for diverse learners.