Medical Dialogue Coding on Medical Dialogue Dataset
0.9SSBERT
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BERTModel Category=transformer-based2025.12 | 0.9 | 0.84 | 0.9 | 0.56 | 0.51 | 0.79 | 0 | 0 | 0.26 | 0 | 0.93 | 0 | |
| DistilBERTModel Category=transformer-based2025.12 | 0.89 | 0.84 | 0.89 | 0.55 | 0.57 | 0.8 | 0 | 0.06 | 0.41 | 0 | 0.93 | 0 | |
| RoBERTaModel Category=transformer-based2025.12 | 0.86 | 0.78 | 0.85 | 0 | 0 | 0.74 | 0 | 0 | 0 | 0 | 0.88 | 0 | |
| GPT-4oModel Category=LLM2025.12 | 0.55 | 0.63 | 0.75 | 0.15 | 0.35 | 0.5 | 0.19 | 0.25 | 0.11 | 0.13 | 0.75 | 0.11 | |
| Qwen3-30BModel Category=LLM, Parameters=30B2025.12 | 0.54 | 0.36 | 0.71 | 0.19 | 0.19 | 0.45 | 0.07 | 0.16 | 0.16 | 0 | 0.65 | 0.1 | |
| Qwen3-8BModel Category=LLM, Parameters=8B2025.12 | 0.4 | 0.24 | 0.57 | 0.11 | 0.12 | 0.62 | 0 | 0.17 | 0 | 0 | 0.58 | 0 | |
| DeepSeek-V3.1Model Category=LLM2025.12 | 0.37 | 0.56 | 0.66 | 0.15 | 0.13 | 0.76 | 0 | 0.13 | 0.14 | 0.09 | 0.73 | 0.13 |