Text Style Transfer On Yelp Review Dataset
Metrics
G-Score (BLEU, Accuracy)
Results
Performance results of various models on this benchmark
Model Name | G-Score (BLEU, Accuracy) | Paper Title | Repository |
|---|---|---|---|
| MultiDecoder | 45.02 | Style Transfer in Text: Exploration and Evaluation | |
| SentiInc | 66.25 | SentiInc: Incorporating Sentiment Information into Sentiment Transfer Without Parallel Data | - |
| StyleEmbedding | 31.31 | Style Transfer in Text: Exploration and Evaluation | |
| CAE | 38.66 | Style Transfer from Non-Parallel Text by Cross-Alignment | |
| DeleteAndRetrieve | 54.64 | Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer | |
| SAE+Discriminator | 74.56 | Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites | |
| LatentOps (Few shot) | 71.6 | Composable Text Controls in Latent Space with ODEs | |
| DeleteOnly | 54.11 | Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer |
0 of 8 row(s) selected.