W-NUT-2020-Shared-Task-2

This is the code implementation of the paper Not-NUTs at W-NUT 2020 Task 2: A BERT-based System in IdentifyingInformative COVID-19 English Tweets.

1. baselines: run the files in the /baselines folder
2. To produce weights for evaluation, please run the files whose names start with finetune<..>, for example, finetuneBERT.py, or has the format <model_name>_BERTweet.py, for example, global_local_BERTweet.py
3. To evaluate a training/finetuning result, please run the files whose names end with _eval.py
4. To view the code for a model's setup, please view files whose names end with _model.py. For example, global_local_BERTweet_model.py