How to Fine-Tune BERT for Text Classification?
This work provides a practical guide for researchers and practitioners in NLP to optimize BERT fine-tuning for text classification tasks, though it is incremental as it builds on existing BERT methods.
The paper tackles the problem of fine-tuning BERT for text classification by investigating different methods and proposes a general solution that achieves new state-of-the-art results on eight widely-studied datasets.
Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing results in many language understanding tasks. In this paper, we conduct exhaustive experiments to investigate different fine-tuning methods of BERT on text classification task and provide a general solution for BERT fine-tuning. Finally, the proposed solution obtains new state-of-the-art results on eight widely-studied text classification datasets.