Source code for Joint Entity and Relation Extraction with Set Prediction Networks. We would appreciate it if you cite our paper as following:
@article{sui2020joint,
title={Joint Entity and Relation Extraction with Set Prediction Networks},
author={Sui, Dianbo and Chen, Yubo and Liu, Kang and Zhao, Jun and Zeng, Xiangrong and Liu, Shengping},
journal={arXiv preprint arXiv:2011.01675},
year={2020}
}
Python: 3.7
PyTorch: >= 1.5.0
Transformers: 2.6.0
- Note That: Replacing BERT_DIR in the command line with the actual directory of BERT-base-cased in your machine!!!
- 注意：需将命令行中的BERT_DIR替换为你机器中实际存储BERT的目录！！！
python -m main --bert_directory BERT_DIR --num_generated_triples 15 --na_rel_coef 1 --max_grad_norm 1 --max_epoch 100 --max_span_length 10python -m main --bert_directory BERT_DIR --num_generated_triples 15 --max_grad_norm 2.5 --na_rel_coef 0.25 --max_epoch 100 --max_span_length 10or
python -m main --bert_directory BERT_DIR --num_generated_triples 15 --max_grad_norm 1 --na_rel_coef 0.5 --max_epoch 100 --max_span_length 10python -m main --bert_directory BERT_DIR --batch_size 4 --num_generated_triples 10 --na_rel_coef 0.25 --max_grad_norm 20 --max_epoch 100 --encoder_lr 0.00002 --decoder_lr 0.00005 --num_decoder_layers 4 --max_span_length 10 --weight_decay 0.000001 --lr_decay 0.02Model parameters can be download in Baidu Pan (key: SetP) 😎