Fairness and Responsibility in Machine Learning at Google. Previously Principal Data Scientist at Opower. Always available for data science mentoring or advice.
Jan 29, 2020 • 9 tweets • 7 min read
Talk by Chris Sweeney at #FAT2020 on "Reducing sentiment polarity for demographic attributes in word embeddings using adversarial learning," with @Maryam_Najafian.
There are several types of bias encoded in language models, and this paper focuses on sentiment bias, where certain identity terms encode a more positive sentiment than others. #FAT2020