Aspect-Based Sentiment Analysis on SemEval 2016
63.23Accuracy (FR)MTL-MSMO-DISTLL
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MTL-MSMO-DISTLLBackbone=XLM-R2025.02 | 63.23 | 70.95 | 66.24 | 64.36 | 66.2 | |
| MTL-CL-XABSA-DISTILLBackbone=XLM-R2025.02 | 62.37 | 70.58 | 65.98 | 62.79 | 65.43 | |
| MTL-MSMOBackbone=XLM-R2025.02 | 60.93 | 69.34 | 64.85 | 64.17 | 64.82 | |
| MTL-CL-XABSABackbone=XLM-R2025.02 | 60.09 | 68.88 | 64.16 | 63.07 | 64.05 | |
| MTL-MSMO-DISTLLBackbone=mBERT2025.02 | 54.56 | 62.69 | 55.56 | 56.19 | 57 | |
| MTL-CL-XABSA-DISTLLBackbone=mBERT2025.02 | 53.03 | 62.19 | 54.25 | 54.63 | 56.03 | |
| MTL-MSMOBackbone=mBERT2025.02 | 51.33 | 60.43 | 53.68 | 51.89 | 54.33 | |
| MTL-CL-XABSABackbone=mBERT2025.02 | 50.01 | 59.05 | 51.22 | 50.59 | 52.72 |