BERT-NER
BERT-NER copied to clipboard
Wrong output format for evaluation script
The conlleval.pl
script accepts input file format like <span> <groundtruth> <prediction>
, but the model's output is <span> <prediction> <groundtruth>
. Although it doesn't affect the F1 score, it swaps the values of precision and recall.
Yes, you are right thank you for your help for this hidden problem. I will update it.