This repository contains the data and code introduced in the paper "CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models" (EMNLP 2020).
In line 34-39, sent_more and sent_less get flipped if they have antistereo direction, but when calculating the score for the antistereo direction, you compare if score['sent2_score'] > score['sent1_score']: in line 239, essentially flipping them back and doing the same comparison as with the stereo direction. Is this right? To my understanding, you want to flip the comparison for pairs with antistereo direction, since the stereotypical sentence is sent_less in these pairs.
if direction == 'stereo':
sent1 = row['sent_more']
sent2 = row['sent_less']
else:
sent1 = row['sent_less']
sent2 = row['sent_more']
In line 34-39,
sent_more
andsent_less
get flipped if they haveantistereo
direction, but when calculating the score for theantistereo
direction, you compareif score['sent2_score'] > score['sent1_score']:
in line 239, essentially flipping them back and doing the same comparison as with thestereo
direction. Is this right? To my understanding, you want to flip the comparison for pairs withantistereo
direction, since the stereotypical sentence issent_less
in these pairs.