Research Article
Mapping Relationship Discovery of Multidimensional Architectures in Autonomous Transportation System Based on Text-Matching Model
Table 9
The performance for the combination of Bi-LSTM and CNN.
| | No | Text-matching model | Precision (%) | Recall (%) | F1 (%) |
| | 1 | Siamese-BERT-wwm-Bi-LSTM-CNN | 86.37 | 85.37 | 85.87 | | 2 | Siamese-BERT-wwm-CNN-Bi-LSTM | 80.80 | 81.03 | 80.91 | | 3 | Siamese-BERT-wwm-CNN + Bi-LSTM | 86.41 | 86.12 | 86.27 | | 4 | Siamese-BERT-wwm-CNN | 86.65 | 86.18 | 86.41 | | 5 | Siamese-BERT-wwm-Bi-LSTM | 87.30 | 88.35 | 87.82 |
|
|
Bold values refer to the maximum prediction performance in each circumstance.
|
