Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
This work addresses the need for efficient NLP models for resource-constrained applications, though it is incremental as it builds on existing distillation techniques.
The paper tackled the problem of making lightweight neural networks competitive with deep models like BERT by distilling knowledge from BERT into a single-layer BiLSTM, achieving comparable results to ELMo with 100 times fewer parameters and 15 times faster inference across multiple NLP tasks.
In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representation model, which includes BERT, ELMo, and GPT. These developments have led to the conviction that previous-generation, shallower neural networks for language understanding are obsolete. In this paper, however, we demonstrate that rudimentary, lightweight neural networks can still be made competitive without architecture changes, external training data, or additional input features. We propose to distill knowledge from BERT, a state-of-the-art language representation model, into a single-layer BiLSTM, as well as its siamese counterpart for sentence-pair tasks. Across multiple datasets in paraphrasing, natural language inference, and sentiment classification, we achieve comparable results with ELMo, while using roughly 100 times fewer parameters and 15 times less inference time.