I am new to Deep learning based NLP and I have a doubt - I am trying to build a NER model and I found some journals where people are relying on BERT-BiLSTM-CRF model for it. As far as I know BERT is a language model that scans the contexts in both the directions and embeds words according to the context. Now my question is - if context is captured during word embedding with BERT, why do we need another layer of BiLSTM?


1 Answer 1


That layer isn't required indeed as it also encodes the sequence, albeit in a different way than BERT.

What I assume is that in a BERT-BiLSTM-CRF, setup, the BERT layer is either frozen or difficult to fine-tune due to its sheer size. Which is likely why the BiLSTM layer has been added there.

  • $\begingroup$ Hmmm... that makes sense. Thanks for the reply. $\endgroup$ Commented Jan 6, 2021 at 8:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.