Hello,
I am using Flair to produce contextual embeddings, which are fed into a Bi-LSTM-CRF model for sequence labeling task. Are the parameters of Flair are fixed during the training? or they are updated jointly with the parameters of the main model?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Hello, I am using Flair to produce contextual embeddings, which are fed into a Bi-LSTM-CRF model for sequence labeling task. Are the parameters of Flair are fixed during the training? or they are updated jointly with the parameters of the main model?
Thank you in advance!