Table 9 Comparative experiments of different prompting methods on Laptop dataset.
From: Graph-enhanced implicit aspect-level sentiment analysis based on multi-prompt fusion
Method | P | R | F1 |
|---|---|---|---|
T5 | 43.90 | 42.76 | 43.32 |
Fixed-sequence prompt | 44.91 | 43.19 | 44.03 |
Multi-prompt fusion | 46.12 | 44.84 | 45.47 |
