@inproceedings{bai-etal-2021-pre,
    title = "Pre-train or Annotate? Domain Adaptation with a Constrained Budget",
    author = "Bai, Fan  and
              Ritter, Alan  and
              Xu, Wei",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
}

git clone https://github.com/bflashcp3f/ProcBERT.git
cd ProcBERT
conda env create -f environment.yml
conda activate procbert

# After downloading the data, update the DATA_PATH variable in code/utils.py
DATA_PATH=<DATA_PATH>

# Named Entity Recognition (NER) 
python code/ner_da_budget.py     \
  --lm_model procbert     \
  --src_data pubmed     \
  --tgt_data chemsyn     \
  --gpu_ids 0,1   \
  --output_dir ./output/da/pubmed_chemsyn     \
  --learning_rate 1e-5     \
  --task_name fa_ner     \
  --batch_size 16     \
  --max_len 512    \
  --epochs 25 \
  --budget 700 \
  --alpha 1   \
  --save_model

# Relation Extraction (RE)
python code/rel_da_budget.py \
  --lm_model procbert \
  --src_data pubmed     \
  --tgt_data chemsyn     \
  --gpu_ids 0,1  \
  --output_dir ./output/da/pubmed_chemsyn \
  --learning_rate 1e-5 \
  --task_name fa_rel \
  --batch_size 48 \
  --max_len 256 \
  --epochs 5 \
  --budget 700 \
  --alpha 1 \
  --down_sample \
  --down_sample_rate 0.4 \
  --save_model

# NER
sh script/ner/run_ner_da_budget_all.sh

# RE
sh script/rel/run_rel_da_budget_all.sh

# Named Entity Recognition (NER) 
python code/ner_budget.py \
  --lm_model procbert \
  --data_name chemsyn \
  --gpu_ids 0,1  \
  --output_dir ./output/chemsyn \
  --learning_rate 1e-5 \
  --task_name ner \
  --batch_size 16 \
  --max_len 512 \
  --epochs 25 \
  --budget 700 \
  --save_model

# Relation Extraction (RE)
python code/rel_budget.py \
  --lm_model procbert \
  --data_name chemsyn \
  --gpu_ids 0,1  \
  --output_dir ./output/chemsyn \
  --learning_rate 1e-5 \
  --task_name rel \
  --batch_size 48 \
  --max_len 256 \
  --epochs 5 \
  --budget 700 \
  --down_sample \
  --down_sample_rate 0.4 \
  --save_model

# NER
sh script/ner/run_ner_budget_all.sh

# RE
sh script/rel/run_rel_budget_all.sh

# Named Entity Recognition (NER) 
python code/ner.py \
  --lm_model procbert \
  --data_name chemsyn \
  --gpu_ids 0,1  \
  --output_dir ./output/chemsyn \
  --learning_rate 1e-5 \
  --task_name ner \
  --batch_size 16 \
  --max_len 512 \
  --epochs 20 \
  --save_model

# Relation Extraction (RE)
python code/rel.py \
  --lm_model procbert \
  --data_name chemsyn \
  --gpu_ids 0,1  \
  --output_dir ./output/chemsyn \
  --learning_rate 1e-5 \
  --task_name rel \
  --batch_size 48 \
  --max_len 256 \
  --epochs 5 \
  --down_sample \
  --down_sample_rate 0.4 \
  --save_model

# NER
sh script/ner/run_ner_all.sh

# RE
sh script/rel/run_rel_all.sh