Closed fpcsong closed 2 years ago
Thanks for your nice work for erc, in the file src/DialogEvaluator_emory.py line 145, macro f1 only contains 6 labels, without the neutral
src/DialogEvaluator_emory.py
neutral
macro_f1 = metrics.f1_score( pred_list, grd_list, labels=[1, 2, 3, 4, 5, 6], average='weighted') logging.info("Weighted F1-macro with neutral: {:.4f} ({}/{})\n".format(macro_f1, correct, total))
labels here should be [0, 1, 2, 3, 4, 5, 6]
Also, metrics.f1_score was used in a wrong way, see doc
Hi, thanks for finding this error. I have trained a new model and updated the results, please check.
Thanks for your nice work for erc, in the file
src/DialogEvaluator_emory.py
line 145, macro f1 only contains 6 labels, without theneutral
labels here should be [0, 1, 2, 3, 4, 5, 6]