Research Article
KoRASA: Pipeline Optimization for Open-Source Korean Natural Language Understanding Framework Based on Deep Learning
Table 9
Performance comparison of entity extraction.
| Model | Intent classification | Entity extraction | Train | Test | Train | Test | Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 |
| CRF | 1.000 | 1.000 | 0.974 | 0.969 | 0.993 | 0.989 | 0.964 | 0.905 | DIET-Base + CRF | 1.000 | 1.000 | 0.976 | 0.972 | 0.993 | 0.989 | 0.964 | 0.904 | DIET-Base | 1.000 | 1.000 | 0.982 | 0.980 | 0.993 | 0.989 | 0.962 | 0.910 | KoRASA | 1.000 | 1.000 | 0.982 | 0.984 | 0.993 | 0.989 | 0.974 | 0.947 |
|
|