most citedGender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task

29 citations · 52 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2023★ 29 cited

Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task

Sophie Jentzsch, Cigdem Turan

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, ha…

cs.CL2019★ 17 cited

BERT has a Moral Compass: Improvements of ethical and moral values of machines

Patrick Schramowski, Cigdem Turan, Sophie Jentzsch +2

Allowing machines to choose whether to kill humans would be devastating for world peace and security. But how do we equip machines with the ability to learn ethical or even moral c…