Chinese Named Entity Recognition On Ontonotes
Metrics
F1
Precision
Recall
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | F1 | Precision | Recall |
|---|---|---|---|
| nflat-non-flat-lattice-transformer-for | 77.21 | 75.17 | 79.37 |
| chinese-ner-using-lattice-lstm | 73.88 | - | - |
| a-lexicon-based-graph-neural-network-for | 74.89 | 76.13 | 73.68 |
| flat-chinese-ner-using-flat-lattice | 76.45 | - | - |
| slk-ner-exploiting-second-order-lexicon | 80.2 | - | - |
| simplify-the-usage-of-lexicon-in-chinese-ner | 75.54 | - | - |
| unified-named-entity-recognition-as-word-word | 83.08 | - | - |
| boundary-smoothing-for-named-entity-1 | 82.83 | - | - |
| improving-named-entity-recognition-with | 81.18 | - | - |
| can-ner-convolutional-attention-network | 73.64 | 75.05 | 72.29 |
| a-unified-mrc-framework-for-named-entity | 82.11 | - | - |
| flat-chinese-ner-using-flat-lattice | 81.82 | - | - |
| fgn-fusion-glyph-network-for-chinese-named | 82.04 | - | - |
| dice-loss-for-data-imbalanced-nlp-tasks | 84.47 | - | - |
| glyce-glyph-vectors-for-chinese-character | 80.62 | 81.87 | 81.4 |