Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models

In this paper, we explore the knowledge distillation approach under the multi-task learning setting. We distill the BERT model refined by multi-task learning on seven datasets of the GLUE benchmark into a bidirectional LSTM with attention mechanism. Unlike other BERT distillation methods which specifically designed for Transformer-based architectures, we provide a general learning framework. Our approach is model agnostic and can be easily applied on different future teacher models. Compared to a strong, similarly BiLSTM-based approach, we achieve better quality under the same computational constraints. Compared to the present state of the art, we reach comparable results with much faster inference speed.