Debiasing Personal Identities in Toxicity Classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Joint Mitigation of Interactional Bias
Machine learning algorithms have been found discriminative against groups of different social identities, e.g., gender and race. With the detrimental effects of these algorithmic biases, researchers proposed promising ap…
Word EmbeddingsToward Understanding Bias Correlations for Mitigation in NLP
Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have re…
FairnessWord EmbeddingsReading Between the Demographic Lines: Resolving Sources of Bias in Toxicity Classifiers
The censorship of toxic comments is often left to the judgment of imperfect models. Perspective API, a creation of Google technology incubator Jigsaw, is perhaps the most widely used toxicity classifier in industry; the …
Detoxifying Language Models with a Toxic Corpus
Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily cate…
Text GenerationChallenges in Automated Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods…
Fairnesstext-classificationText Classification