Chinese Named Entity Recognition On Weibo Ner
Métriques
F1
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | F1 |
|---|---|
| chinese-ner-using-lattice-lstm | 58.79 |
| tener-adapting-transformer-encoder-for-name | 58.17 |
| slk-ner-exploiting-second-order-lexicon | 64 |
| flat-chinese-ner-using-flat-lattice | 68.55 |
| fgn-fusion-glyph-network-for-chinese-named | 71.25 |
| glyce-glyph-vectors-for-chinese-character | 67.6 |
| locate-and-label-a-two-stage-identifier-for | 69.16 |
| improving-named-entity-recognition-with | 69.78 |
| leverage-lexical-knowledge-for-chinese-named | 63.09 |
| boundary-smoothing-for-named-entity-1 | 72.66 |
| a-global-context-mechanism-for-sequence | 70.98 |
| adversarial-transfer-learning-for-chinese | 53.08 |
| named-entity-recognition-for-social-media | 69.8 |
| flat-chinese-ner-using-flat-lattice | 60.32 |
| improving-named-entity-recognition-by | 72.77 |
| can-ner-convolutional-attention-network | - |
| simplify-the-usage-of-lexicon-in-chinese-ner | 61.24 |
| nflat-non-flat-lattice-transformer-for | 61.94 |