This is for EMNLP2020 findings paper: Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
- python 3.7/3.8
- pytorch 1.6
pip install -r requirements.txtpip install -e .Download the DuIE dataset from official website
Unzip *.json into ./raw_data/chinese/
For NYT, see raw_data/nyt/README.md
pip install -r requirements.txtcd raw_data
unzip ../raw_data_joint.zipThen run data_split for both datasets:
python data_split.pybash train_all.shseperate steps:
python main.py --mode preprocessing --exp chinese_seq2umt_ops
python main.py --mode train --exp chinese_seq2umt_ops
python main.py --mode evaluation --exp chinese_seq2umt_opspython main.py --mode preprocessing --exp nyt_seq2umt_ops
python main.py --mode train --exp nyt_seq2umt_ops
python main.py --mode evaluation --exp nyt_seq2umt_opspython main.py --mode preprocessing --exp nyt_wdec
python main.py --mode train --exp nyt_wdec
python main.py --mode evaluation --exp nyt_wdec
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent