Exploration of BERT-BiLSTM models with Layer Aggregation (attention-based and capsule-routing-based) and Hidden-State Aggregation (attention-based and capsule-routing-based).
Thank you for your help, I successfully ran the program with my own data.
I would like to ask, is your bert original or is it pre-trained with tweet data in the target domain?
If it was pre-trained with tweet data in the later stage, can you probably tell me how to train?