Table 2 Experimental results on the Restaurant dataset.
From: Graph-enhanced implicit aspect-level sentiment analysis based on multi-prompt fusion
| Â | Methods | Precision (%) | Recall (%) | F1 (%) |
|---|---|---|---|---|
Extractive methods | DP-ACOS | 34.67 | 15.08 | 21.04 |
Extract-Classify-ACOS | 38.54 | 52.96 | 44.61 | |
SGTS | 55.20 | 43.70 | 48.80 | |
Generative | Paraphrase | N/A | N/A | \(\underline{61.16}\) |
Seq2Path | N/A | N/A | 58.41 | |
Special_Symbols+ UAUL | \(\underline{61.22}\) | 59.87 | 60.53 | |
DLO + UAUL | 61.03 | \(\underline{60.55}\) | 60.78 | |
ILO + UAUL | 59.46 | 59.12 | 59.29 | |
BART-CRN | 50.84 | 47.10 | 48.90 | |
The approach in this paper | 63.69(\(\uparrow\) 2.47 ) | 62.63(\(\uparrow\) 2.08 ) | 63.15(\(\uparrow\) 1.99 ) |
