Table 2.
Results by all models.
ModelENERCoNLL-2003
P (%)R (%)F1(%)P (%)R (%)F1(%)
BiGRU 62.15 68.65 65.28 89.71 90.97 90.24 
BiLSTM-CNN 62.78 69.99 66.45 91.89 91.48 91.62 
BiLSTM-CRF 63.92 70.13 66.94 92.05 91.62 91.78 
SL-BERT 66.37 72.67 69.01 91.93 91.54 91.73 
SL-BART 65.56 73.20 68.98 89.60 91.63 90.60 
Template-BART 65.15 74.28 70.03 90.51 93.34 91.90 
FewNER 64.82 73.78 69.54 90.94 92.59 91.32 
Model-Fusion 64.18 73.92 69.37 89.91 91.89 90.47 
MCP-NER 68.03 75.34 72.45 92.48 93.08 92.72 
 w/o prompt 67.41 74.11 71.28 91.87 92.42 92.05 
 input prefix prompt 67.32 74.47 71.39 92.03 92.79 92.49 
 w/o ML 65.69 72.26 69.59 91.32 91.97 91.66 
ModelENERCoNLL-2003
P (%)R (%)F1(%)P (%)R (%)F1(%)
BiGRU 62.15 68.65 65.28 89.71 90.97 90.24 
BiLSTM-CNN 62.78 69.99 66.45 91.89 91.48 91.62 
BiLSTM-CRF 63.92 70.13 66.94 92.05 91.62 91.78 
SL-BERT 66.37 72.67 69.01 91.93 91.54 91.73 
SL-BART 65.56 73.20 68.98 89.60 91.63 90.60 
Template-BART 65.15 74.28 70.03 90.51 93.34 91.90 
FewNER 64.82 73.78 69.54 90.94 92.59 91.32 
Model-Fusion 64.18 73.92 69.37 89.91 91.89 90.47 
MCP-NER 68.03 75.34 72.45 92.48 93.08 92.72 
 w/o prompt 67.41 74.11 71.28 91.87 92.42 92.05 
 input prefix prompt 67.32 74.47 71.39 92.03 92.79 92.49 
 w/o ML 65.69 72.26 69.59 91.32 91.97 91.66 

Note: Here P, R, and F1 denote Precision, Recall, and F1 score, respectively.

View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept