List your company
ResearchFormerly WizWand

Named Entity Recognition on CoNLL Dutch 2002 original (test)

95.21F1 ScoreTransformer-Linear
89.656491.098292.5493.9818Nov 13, 2020
Updated 8mo ago

Evaluation results

MethodLinks
Transformer-LinearApproach=Fine-tuning (Ablations), Document features=yes (+enforce)2020.1195.21
Transformer-Linear (+DEV)Approach=Fine-tuning (Ablations), Document features=yes (+enforce), Training=Includes dev data2020.1195.19
Transformer-LinearApproach=Fine-tuning, Document features=yes2020.1194.87
Yu et al. (2020)Document features=yes2020.1193.7
Transformer-LinearApproach=Fine-tuning, Document features=no2020.1193.5
Straková et al. (2019)Document features=yes2020.1192.69
LSTM-CRF (all layer mean)Approach=Feature-based, Document features=yes2020.1191.73
Akbik et al. (2019b)Document features=pooling2020.1190.44
LSTM-CRF (all layer mean)Approach=Feature-based, Document features=no2020.1189.87