Text Classification On Yelp 2
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||
|---|---|---|---|
| XLNet | 98.63% | XLNet: Generalized Autoregressive Pretraining for Language Understanding | |
| BERT-ITPT-FiT | 98.08% | How to Fine-Tune BERT for Text Classification? | |
| BERT Finetune + UDA | 97.95% | Unsupervised Data Augmentation for Consistency Training | |
| ULMFiT (Small data) | 97.1% | Sampling Bias in Deep Active Classification: An Empirical Study | |
| COSINE | 95.97% | Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach |
0 of 5 row(s) selected.