Named Entity Recognition On Wnut 2017
평가 지표
F1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | F1 |
|---|---|
| miner-improving-out-of-vocabulary-named-1 | 54.86 |
| a-multi-task-approach-for-named-entity-1 | 41.86 |
| modeling-noisiness-to-recognize-named-1 | 45.55 |
| similarity-based-auxiliary-classifier-for | 44.77 |
| adversarial-self-attention-for-language | 57.3 |
| regularizing-models-via-pointwise-mutual | 42.3 |
| adversarial-self-attention-for-language | 49.8 |
| t-ner-an-all-round-python-library-for-1 | 58.5 |
| a-global-context-mechanism-for-sequence | 59.20 |
| gollie-annotation-guidelines-improve-zero | 54.3 |
| named-entity-recognition-for-social-media | 50.36 |
| robust-named-entity-recognition-with | 52.3 |
| crossweigh-training-named-entity-tagger-from | 50.03 |
| bertweet-a-pre-trained-language-model-for | 56.5 |
| remedying-bilstm-cnn-deficiency-in-modeling | 42.85 |
| improving-named-entity-recognition-by | 59.69 |
| improving-named-entity-recognition-with | 50.68 |
| transfer-learning-and-sentence-level-features | 40.78 |
| inferner-an-attentive-model-leveraging-the | 50.52 |
| improving-named-entity-recognition-by | 60.45 |
| regularizing-models-via-pointwise-mutual | 58.9 |
| hero-gang-neural-model-for-named-entity | 57.41 |
| subregweigh-effective-and-efficient | 60.29 |