Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

  # Download Wikidump
  wget https://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2
  # Download anchor2id
  wget -c https://cloud.tsinghua.edu.cn/f/1c956ed796cb4d788646/?dl=1 -O anchor2id.txt
  # WikiExtractor
  python3 pretrain_data/WikiExtractor.py enwiki-latest-pages-articles.xml.bz2 -o pretrain_data/output -l --min_text_length 100 --filter_disambig_pages -it abbr,b,big --processes 4
  # Modify anchors with 4 processes
  python3 pretrain_data/extract.py 4
  # Preprocess with 4 processes
  python3 pretrain_data/create_ids.py 4
  # create instances
  python3 pretrain_data/create_insts.py 4
  # merge
  python3 code/merge.py

  # extract anchors
  python3 pretrain_data/utils.py get_anchors
  # query Mediawiki api using anchor link to get wikibase item id. For more details, see https://en.wikipedia.org/w/api.php?action=help.
  python3 pretrain_data/create_anchors.py 256 
  # aggregate anchors 
  python3 pretrain_data/utils.py agg_anchors

  python3 code/run_pretrain.py --do_train --data_dir pretrain_data/merge --bert_model ernie_base --output_dir pretrain_out/ --task_name pretrain --fp16 --max_seq_length 256

tar -xvzf kg_embed.tar.gz

tar -xvzf ernie_base.tar.gz

tar -xvzf data.tar.gz

python3 code/run_fewrel.py   --do_train   --do_lower_case   --data_dir data/fewrel/   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 32   --learning_rate 2e-5   --num_train_epochs 10   --output_dir output_fewrel   --fp16   --loss_scale 128
# evaluate
python3 code/eval_fewrel.py   --do_eval   --do_lower_case   --data_dir data/fewrel/   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 32   --learning_rate 2e-5   --num_train_epochs 10   --output_dir output_fewrel   --fp16   --loss_scale 128

python3 code/run_tacred.py   --do_train   --do_lower_case   --data_dir data/tacred   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 32   --learning_rate 2e-5   --num_train_epochs 4.0   --output_dir output_tacred   --fp16   --loss_scale 128 --threshold 0.4
# evaluate
python3 code/eval_tacred.py   --do_eval   --do_lower_case   --data_dir data/tacred   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 32   --learning_rate 2e-5   --num_train_epochs 4.0   --output_dir output_tacred   --fp16   --loss_scale 128 --threshold 0.4

python3 code/run_typing.py    --do_train   --do_lower_case   --data_dir data/FIGER   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 2048   --learning_rate 2e-5   --num_train_epochs 3.0   --output_dir output_figer  --gradient_accumulation_steps 32 --threshold 0.3 --fp16 --loss_scale 128 --warmup_proportion 0.2
# evaluate
python3 code/eval_figer.py    --do_eval   --do_lower_case   --data_dir data/FIGER   --ernie_model ernie_base   --max_seq_length 256   --train_batch_size 2048   --learning_rate 2e-5   --num_train_epochs 3.0   --output_dir output_figer  --gradient_accumulation_steps 32 --threshold 0.3 --fp16 --loss_scale 128 --warmup_proportion 0.2

python3 code/run_typing.py    --do_train   --do_lower_case   --data_dir data/OpenEntity   --ernie_model ernie_base   --max_seq_length 128   --train_batch_size 16   --learning_rate 2e-5   --num_train_epochs 10.0   --output_dir output_open --threshold 0.3 --fp16 --loss_scale 128
# evaluate
python3 code/eval_typing.py   --do_eval   --do_lower_case   --data_dir data/OpenEntity   --ernie_model ernie_base   --max_seq_length 128   --train_batch_size 16   --learning_rate 2e-5   --num_train_epochs 10.0   --output_dir output_open --threshold 0.3 --fp16 --loss_scale 128

python3 code/score.py gold_file pred_file

# If you haven't installed tagme
pip install tagme
# Run example
python3 code/example.py

@inproceedings{zhang2019ernie,
  title={{ERNIE}: Enhanced Language Representation with Informative Entities},
  author={Zhang, Zhengyan and Han, Xu and Liu, Zhiyuan and Jiang, Xin and Sun, Maosong and Liu, Qun},
  booktitle={Proceedings of ACL 2019},
  year={2019}
}