Regarding the training data
I am new to BERT models but don't see annotated training data in the files.
Is there any way to derive the training data from the files, or can you provide the data on which the model is trained?
Thanks in advance.
This isn't my model -- I just uploaded it. The original repo is here: https://github.com/mukut03/ESG-BERT
There is a blog post about the training procedure here: https://towardsdatascience.com/nlp-meets-sustainable-investing-d0542b3c264b
I don't think the training data is publicly released.
In the comments here https://towardsdatascience.com/nlp-meets-sustainable-investing-d0542b3c264b, the author says that the data was curated by the team at Parabole.ai using annual sustainability reports, financial news articles. etc.
Could you please explain how to utilise this trained model?