| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Hierarchical Attentional Hybrid Neural Networks for Document Classification | ✓ Link | 73.28% | HAHNN (CNN) | 2019-01-20 |
| XLNet: Generalized Autoregressive Pretraining for Language Understanding | ✓ Link | 72.95% | XLNet | 2019-06-19 |
| Big Bird: Transformers for Longer Sequences | ✓ Link | 72.16% | BigBird | 2020-07-28 |
| How to Fine-Tune BERT for Text Classification? | ✓ Link | 70.58% | BERT-ITPT-FiT | 2019-05-14 |
| Rethinking Complex Neural Network Architectures for Document Classification | ✓ Link | 68.7% | LSTM-reg (single moedl) | 2019-06-01 |
| Unsupervised Data Augmentation for Consistency Training | ✓ Link | 67.92% | BERT Finetune + UDA | 2019-04-29 |
| Sampling Bias in Deep Active Classification: An Empirical Study | ✓ Link | 67.6% | ULMFiT (Small data) | 2019-09-20 |