References

• 2019HISTORIAE, History of Socio-Cultural Transformation as Linguistic Data Science. A Humanities Use Case16,511 cited
• 2017Semantics derived automatically from language corpora contain human-like biases2,845 cited
• 2021On the Opportunities and Risks of Foundation Models2,670 cited
• 2020Language (Technology) is Power: A Critical Survey of “Bias” in NLP1,044 cited
• 2019On Measuring Social Biases in Sentence Encoders461 cited
• 2019Measuring Bias in Contextualized Word Representations348 cited
• 2021Large image datasets: A pyrrhic win for computer vision?258 cited
• 2021Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development215 cited
• 2021Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases159 cited
• 2020Towards Debiasing Sentence Representations154 cited
• 2017Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English100 cited
• 2020Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias65 cited
• 2021Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle47 cited
• 2021Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers