POS tagging on Ritter11 T-POS (test)
93.4AccuracyACE
Evaluation results
| Method | Links | |
|---|---|---|
| ACEFine-tuning=true, Trained on both train and development set=true2020.10 | 93.4 | |
| XLM-R-largeNormalization strategy=soft2020.05 | 92.6 | |
| XLM-RFine-tuning=true, Trained on both train and development set=true2020.10 | 92.3 | |
| XLM-R-largeNormalization strategy=hard2020.05 | 92.1 | |
| RoBERTa-largeNormalization strategy=soft2020.05 | 91.7 | |
| RoBERTa-largeNormalization strategy=hard2020.05 | 91.5 | |
| DCNNNormalization strategy=hard, Additional training data=WSJ Penn treebank (+a)2020.05 | 91.2 | |
| Gui et al. (2018)2020.10 | 91.2 | |
| TPANNNormalization strategy=hard, Additional training data=WSJ Penn treebank (+a)2020.05 | 90.9 | |
| Gui et al.2020.10 | 90.9 | |
| XLM-R-baseNormalization strategy=soft2020.05 | 90.4 | |
| ARKtaggerNormalization strategy=soft2020.05 | 90.4 | |
| Owoputi et al.2020.10 | 90.4 | |
| XLM-R-baseNormalization strategy=hard2020.05 | 90.3 | |
| BERTweetNormalization strategy=soft2020.05 | 90.1 | |
| Nguyen et al.2020.10 | 90.1 | |
| DCNNNormalization strategy=soft2020.05 | 89.9 | |
| BERTweetNormalization strategy=hard2020.05 | 89.5 | |
| RoBERTa-baseNormalization strategy=soft2020.05 | 88.7 | |
| RoBERTa-baseNormalization strategy=hard2020.05 | 88.3 |