You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to reproduce paper results at the moment. As the paper indicated, I have tried using LIBLINEAR. I could not however find exact details into how each instance is evaluated. I speculated by using n one Vs. all binary classifiers (where n is number of classes) and then sort predictions by estimate value and compare the highest m to the groundtruth (where m is the number of true classes). Still, I got macro F1 score of 16%.
The text was updated successfully, but these errors were encountered:
Hi,
I am trying to reproduce paper results at the moment. As the paper indicated, I have tried using LIBLINEAR. I could not however find exact details into how each instance is evaluated. I speculated by using n one Vs. all binary classifiers (where n is number of classes) and then sort predictions by estimate value and compare the highest m to the groundtruth (where m is the number of true classes). Still, I got macro F1 score of 16%.
The text was updated successfully, but these errors were encountered: