Figure 1.
The Overall Structure of the Model.
Figure 2.
Encoder.
Figure 3.
Label Attention Layer.
Figure 4.
Intent and Slot Interaction Attention layer.
Figure 5.
Feed-forward Network Layer.
Figure 6.
Decoder.
TABLE I.
Model Results of Chinese Dataset CAIS
| Experiment | Model | CAIS | ||
|---|---|---|---|---|
| Slot F1 | Acc | Sent-acc | ||
| 1 | Sloted Gated | 81.8a | 94.3 | 80.5 |
| 2 | Stack-Propagation | 87.8 | 94.7 | 84.7 |
| 3 | SF-ID Network | 84.9 | 94.5 | 82.4 |
| 4 | CM-Net | 86.2 | 94.6 | 84.6 |
| 5 | Co-Interactive Transformer | 88.6 | 95.2 | 86.2 |
| 6 | Our Model | 89.2 | 96.3 | 87.9 |
TABLE II.
Results of Model in Chinese Dataset CAIS
| Model | CAIS | ||
|---|---|---|---|
| Slot F1 | Acc | Sent-acc | |
| Intent➡Slot | 88.4 | 95.8 | 85.5 |
| Slot➡Intent | 88.8 | 95.6 | 85.8 |
| Our Model | 89.2 | 96.3 | 87.9 |
Figure 7.
Sentence-level Analysis