Skip to content
ml-recall

#macro-f1

2 questions from Evaluation Metrics

Timed test

2 questions · 2 min · score and explanations at the end

Take a test
Q 1 / 2Score 0 / 0

Question 1: Short answer

hardAI-checkedEvaluation Metrics

A part-of-speech tagger with three tags has this confusion matrix (rows: true tag, columns: predicted tag):

NN VB ADJ
NN 25 5 1
VB 2 15 12
ADJ 1 6 0

Compute the macro-F1 score as the plain average of the three per-class F1 scores. ADJ has precision and recall 0; count its F1 as 0.

a number, 3 decimals