This is the implemenation of following paper:
DongHyun Choi, Myeong Cheol Shin, EungGyun Kim and Dong Ryeol Shin, OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack, ACL Findings, 2021
https://arxiv.org/abs/2105.05601
tensorflow 2.0
nltk
python main.py --config ./config/config_bilstm.json --store ./train_sample_model --train ./sample/train.txt --dev ./sample/dev.txt --test ./sample/test.txt --attack_num 2