arXiv (Cornell University) · 2017 · 51 citations · 10 references
ComputingComputer ScienceEnglishComputational LinguisticsNatural Language ProcessingText AnalyticsAlgorithmic FairnessComputational Text AnalysisEthnic MinoritiesFairness In Machine LearningSentiment AnalysisText PreprocessingFairness In Language ModelsLinguistic Disparities
We highlight an important frontier in algorithmic fairness: disparity in the quality of natural language processing algorithms when applied to language from authors of different social groups. For example, current systems sometimes analyze the language of females and minorities more poorly than they do of whites and males. We conduct an empirical analysis of racial disparity in language identification for tweets written in African-American English, and discuss implications of disparity in NLP.
10
Certifying and Removing Disparate Impact
Michael Feldman, Sorelle A. Friedler, John Moeller et al. · 2015 · 1.8K citations
Gender and Dialect Bias in YouTube's Automatic Captions
Rachael Tatman · 2017 · 321 citations · Full text
The Social Impact of Natural Language Processing
Dirk Hovy, Shannon Spruit · 2016 · 311 citations