BioCreative'21, Task 3 - Automatic extraction of medication names in tweets Forum

Go back to competition Back to thread list Post in this thread

> Inter Annotator Agreements

Are there inter-annotator agreements at the named entity level? I saw the reference ("Deep neural networks ensemble for detecting medication mentions in tweets"), but I couldn't find this. For example, do we know what precision, recall, f1-score there would be if one used the annotations from one annotator as the gold standard and the annotations of a second annotator as the predictions?
Thanks in advance,
Best regards,
Diego

Posted by: diego_s @ May 19, 2021, 3:33 p.m.
Post in this thread