Pre-training for SQUAD and fine-tuning for BIOASQ

[rsanjaykamath]

Hello,

Can you please explain how exactly can one replicate the state of the results on BIOASQ dataset, as you report in the paper that you pre-train on SQUAD before fine tuning on BIOASQ. I tried doing the same steps reported in this repo and found the results to be quite low if not pre-trained on SQUAD, which is normal.

Is there any doc which explains the commands to do this? I'm sorry if I missed reading this.

Thanks

[jhyuklee]

As Wonjin said, to reproduce our results, you need to follow a few steps below.

1. Fine-tune BioBERT on SQuAD dataset (https://github.com/google-research/bert)
2. Use ckpt of step1 as initial checkpoint for fine-tunning BioASQ datasets. (Be sure to set output folder as new one)

Thanks.

[telukuntla]

Hello @jhyuklee ,
May I know what are the parameters you have used while training it on Squad. like epochs and learning rate..

[sonigovind]

As I have a dataset for NER, Which is containing three features like seq, word, and tag and now I want to use the NER task so how can I use this model for my work?