Aspect Based Sentiment Analysis On Semeval
Métriques
Laptop (Acc)
Mean Acc (Restaurant + Laptop)
Restaurant (Acc)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Laptop (Acc) | Mean Acc (Restaurant + Laptop) | Restaurant (Acc) |
|---|---|---|---|
| back-to-reality-leveraging-pattern-driven | 86.21 | 88.27 | 90.33 |
| attentional-encoder-network-for-targeted | 79.93 | 81.53 | 83.12 |
| multi-grained-attention-network-for-aspect | 75.39 | 78.32 | 81.25 |
| adversarial-training-for-aspect-based | 79.35 | 82.69 | 86.03 |
| aspect-level-sentiment-classification-with-1 | 72.21 | 76.58 | 80.95 |
| improving-bert-performance-for-aspect-based | 79.55 | 82.96 | 86.37 |
| attentional-encoder-network-for-targeted | 78.99 | 81.73 | 84.46 |
| interactive-attention-networks-for-aspect | 72.10 | 75.35 | 78.60 |
| exploiting-typed-syntactic-dependencies-for | 81.25 | 83.92 | 86.59 |
| masking-the-bias-from-echo-chambers-to-large | 86.24 | 86.95 | 87.65 |
| semi-supervised-target-level-sentiment | 75.34 | 78.22 | 81.10 |
| transformation-networks-for-target-oriented | 76.01 | - | 80.79 |
| a-position-aware-bidirectional-attention | 74.12 | 77.64 | 81.16 |
| effective-attention-modeling-for-aspect-level | 71.94 | 76.29 | 80.63 |
| attentional-encoder-network-for-targeted | 73.51 | 77.25 | 80.98 |
| attention-and-lexicon-regularized-lstm-for | - | - | 82.86 |
| aspect-based-sentiment-analysis-using-bitmask | 74.9 | 78.1 | 81.3 |
| bert-post-training-for-review-reading | 78.07 | 81.51 | 84.95 |
| rvisa-reasoning-and-verification-for-implicit | 86.68 | 89.10 | 91.52 |
| progressive-self-supervised-attention | 77.62 | 79.58 | 81.53 |
| a-multi-task-learning-model-for-chinese | 82.29 | 86.24 | 90.18 |
| modeling-sentiment-dependencies-with-graph | 81.35 | 82.46 | 83.57 |
| multi-task-learning-with-llms-for-implicit | 85.74 | 89.21 | 92.68 |
| hierarchical-attention-based-position-aware | 77.27 | 79.75 | 82.23 |
| effective-lstms-for-target-dependent | 68.13 | 71.88 | 75.63 |
| you-only-read-once-constituency-oriented | 81.82 | 84.48 | 87.14 |
| exploiting-document-knowledge-for-aspect | 71.15 | 75.13 | 79.11 |
| attention-based-lstm-for-aspect-level | 68.70 | 72.95 | 77.20 |
| aspect-sentiment-classification-with-aspect | 77.64 | 80.25 | 82.86 |
| understand-me-if-you-refer-to-aspect | 81.87 | 84.61 | 87.35 |
| target-sensitive-memory-networks-for-aspect | 72.43 | 74.08 | 75.73 |
| recurrent-attention-network-on-memory-for | 74.49 | 77.36 | 80.23 |
| aspect-based-sentiment-analysis-using-bert | 82,76 | 86,11 | 89,46 |
| adapt-or-get-left-behind-domain-adaptation | 80.23 | 84.06 | 87.89 |
| does-syntax-matter-a-strong-baseline-for | 83.78 | 85.58 | 87.37 |
| towards-unifying-the-label-space-for-aspect | 81.96 | 85.75 | 89.54 |
| aspect-level-sentiment-classification-with | 74.5 | 77.85 | 81.20 |
| transformation-networks-for-target-oriented | 76.01 | 78.4 | 80.79 |
| learning-latent-opinions-for-aspect-level | 75.1 | 78.35 | 81.6 |
| attention-and-lexicon-regularized-lstm-for | - | - | 82.62 |
| iarm-inter-aspect-relation-modeling-with | 73.8 | 77.02 | 80.0 |
| left-center-right-separated-neural-network | 75.24 | 78.29 | 81.34 |
| does-bert-understand-sentiment-leveraging | - | - | 86.20 |
| an-interactive-multi-task-learning-network | 75.36 | 79.63 | 83.89 |
| parameterized-convolutional-neural-networks-1 | 70.06 | 74.63 | 79.20 |
| exploiting-coarse-to-fine-task-transfer-for | 76.21 | 78.85 | 81.49 |
| instructabsa-instruction-learning-for-aspect | 80.56 | 81.5 | 82.44 |
| target-sensitive-memory-networks-for-aspect | 71.79 | 75.29 | 78.79 |