Test Set Sampling Affects System Rankings: Expanded Human Evaluation of WMT20 English-Inuktitut Systems.

Rebecca Knowles Chi-kiu Lo

Published in: WMT (2022)

Keyphrases

test set
error rate
training set
evaluation methodology
training data
class distribution
database
object detection
random selection
machine learning
learning algorithm
computer vision
decision trees
language model
evaluation method
human judgments