Allan Jie

Got it. Maybe should specify them in the table/paper? From the table, it seems only those marked with "*" are train-test split.

In the SVAMP paper, the appendix A show that the transformers with Roberta encoder obtain 38.9 accuracy  But it seems the RobertaGen only get 30.3 here. Curious about the...

Thanks. Can you let me know which version of this repo you are using? (PyTorch or DyNet)?

Are you able to overfit your dataset with a normal lstm crf model?

I did not train ELMo but using existing pretrained ELMo model from different languages. Usually people pretrain them following the code add provided by AllenNLP, let me know if you...

Any updates on this?

Thanks. Is it possible to provide the details about how you did it for this dataset? I think this could be important to reproduce the performance and better help the...

Changing 4 to 3 works for me though. 😞

Sorry for the late reply, but which layer of the hidden state you use? average or the final layer

Thanks, I also found `weighted average` in [neuralnets/ELMoWordEmbeddings.py](https://github.com/UKPLab/elmo-bilstm-cnn-crf/blob/HEAD/neuralnets/ELMoWordEmbeddings.py#L104), can I ask why it is just simply swaping the axes? If I'm not wrong, the `0` dimension is the layer and...