Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT

Fine-tuned variants of BERT are able to achieve state-of-the-art accuracy on many natural language processing tasks, although at significant computational costs. In this paper, we verify BERT{'}s effectiveness for document classification and investigate the extent to which BERT-level effectiveness can be obtained by different baselines, combined with knowledge distillation{---}a popular model compression method. The results show that BERT-level effectiveness can be achieved by a single-layer LSTM with at least $40\times$ fewer FLOPS and only ${\sim}3\%$ parameters. More importantly, this study analyzes the limits of knowledge distillation as we distill BERT{'}s knowledge all the way down to linear models{---}a relevant baseline for the task. We report substantial improvement in effectiveness for even the simplest models, as they capture the knowledge learnt by BERT.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods