BERT-BiLSTM-CRF-NER
BERT-BiLSTM-CRF-NER copied to clipboard
训练过程具体是怎么样的
我用您的模型在自己的模型上训练, 请问训练过程是
- random initialization -> fine-tuning with a fixed learning rate 还是
- freezing the BERT part and training the BiLSTM-CRF part -> fine-tuning the whole network with a small learning rate
因为有看到测试的时候似乎用用原BERT的representation 的