arXiv:1908.05757
Debiasing Personal Identities in Toxicity Classification
원문 초록
As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias minimization by measuring not only the models performance on our dataset as a whole, but also how it performs across different subgroups. This requires measuring per-formance independently for different demographic subgroups and measuring bias by comparing them to results from the rest of our data. We show how unintended bias can be detected using these metrics and how removing bias from a dataset completely can result in worse results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ExploreKit: Automatic Feature Generation and Selection
Thumbs up? Sentiment Classification using Machine Learning Techniques
Analysis of Kepler Objects of Interest using Machine Learning for Exoplanet Identification
Twitter Sentiment Analysis
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.