Sentiment Analysis On Yelp Binary
Métriques
Error
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Error |
|---|---|
| disconnected-recurrent-neural-networks-for | 2.73 |
| supervised-and-semi-supervised-text | 2.9 |
| unsupervised-data-augmentation-1 | 1.89 |
| how-to-fine-tune-bert-for-text-classification | 1.81 |
| universal-language-model-fine-tuning-for-text | 2.16 |
| character-level-convolutional-networks-for | 4.88 |
| joint-embedding-of-words-and-labels-for-text | 4.69 |
| bag-of-tricks-for-efficient-text | 4.3 |
| learning-to-remember-more-with-less | 3.60 |
| deep-pyramid-convolutional-neural-networks | 2.64 |
| squeezed-very-deep-convolutional-neural | 4.74 |
| compositional-coding-capsule-network-with-k | 3.52 |
| gpu-kernels-for-block-sparse-weights | 3.27 |
| how-to-fine-tune-bert-for-text-classification | 1.92 |
| sliced-recurrent-neural-networks | 3.96 |
| unsupervised-data-augmentation-1 | 2.05 |
| heavy-tailed-representations-text-polarity | 1.86 |
| baseline-needs-more-love-on-simple-word | 4.19 |
| learning-context-sensitive-convolutional | 3.89 |
| xlnet-generalized-autoregressive-pretraining | 1.37 |