The BERT model seems trained from the dataset itself?

brightmart / text_classification

all kinds of text classification models and more with deep learning

MIT License

7.87k stars 2.57k forks source link

The BERT model seems trained from the dataset itself? #136

Open acadTags opened 5 years ago

acadTags commented 5 years ago

I had a general look at the BERT code. If I am not wrong, the BERT model in this folder is simply trained from the data itself, rather than transferred from a huge corpus? Could you help clarify this part?