Open rspiewak47 opened 3 years ago
Same. I need to fine tune the model to recognize the sentiment for specific words in a specific domain/meaning. I suspect that this can be done by using transfer learning on their trained Dense layer and preserving the pre-trained BERT layer. However, it would be very helpful if the author of the library could verify and indicate a good way to do it.
I need to have the polarity associated with particular words or phrases used to ensure that these are taken into account when associated with a particular aspect. Is there a way to do this?