Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets.

Philippe Laban Chien-Sheng Wu Wenhao Liu Caiming Xiong

Published in: EMNLP (2022)

Keyphrases

evaluation method
database
virtual world
human subjects
positive and negative
data sets
uci machine learning repository
human judgments
evaluation methods
gold standard
three dimensional
benchmark datasets
human experts
training set
evaluation metrics
case study
decision trees
learning algorithm
real world