Distilling Task Specific Knowledge from BERT into Simple Neural Networks (paper explained)

As natural language models are getting increasingly larger like BERT, ELMo, XLNET, and GPT. This paper demonstrates that light-weight neural networks can still be made competitive without architecture changes.

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks Paper: https://arxiv.org/abs/1903.12136

Abstract 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. ... https://www.youtube.com/watch?v=AKCPPvaz8tU