MetaAug4NER
Robust Self-augmentation for NER with Meta-reweighting
Train
// 中文ontonote4 采样5%的数据
python train_reweight.py --cuda 1 -lr 1e-3 --bert_lr 2e-5
--batch_size 4 --aug_batch_size 8 --update_step 1 --patient 3
--genre onto_5 --aug_genre onto_5_repl1 --train_type aug
&> onto_5.log &
Related Work
- Learning to Reweight Examples for Robust Deep Learning
- Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
- Distilling Effective Supervision from Severe Label Noise
- Meta Soft Label Generation for Noisy Labels
- Meta Label Correction for Noisy Label Learning