Table 3 Accuracy comparison among models (%)
From: Few-shot relation classification by context attention-based prototypical networks with BERT
Model | 5 way 5 shot | 5 way 10 shot | 10 way 5 shot | 10 way 10 shot |
|---|---|---|---|---|
Meta network(CNN) | 80.03 ±0.52 | 82.96 ± 0.50 | 70.31 ± 0.48 | 73.03 ± 0.44 |
GNN(CNN) | 77.75 ± 0.44 | 80.56 ± 0.38 | 66.02 ± 0.40 | 69.30 ± 0.42 |
SNAIL(CNN) | 80.57 ± 0.24 | 81.62 ± 0.21 | 68.03 ± 0.22 | 71.32± 0.20 |
Prototypical networks(CNN) | 85.57 ± 0.14 | 88.17 ± 0.10 | 75.01 ± 0.16 | 78.50 ± 0.11 |
Proto_HATT(CNN) | 87.23 ± 0.08 | 89.53 ± 0.06 | 77.45 ± 0.06 | 80.98 ± 0.08 |
Proto_CATT_BERT(CNN) | 94.86 ± 0.04 | 95.74 ± 0.05 | 90.01 ±0.04 | 91.60 ± 0.03 |