Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

9 March 2019

Papers citing "Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them"

8 / 308 papers shown

Title
Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function Yusu Qian Urwa Muaz Ben Zhang J. Hyun FaML 27 95 0 30 May 2019
Racial Bias in Hate Speech and Abusive Language Detection Datasets Thomas Davidson Debasmita Bhattacharya Ingmar Weber 25 452 0 29 May 2019
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems Alex Jinpeng Wang Yada Pruksachatkun Nikita Nangia Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 49 2,260 0 02 May 2019
Evaluating the Underlying Gender Bias in Contextualized Word Embeddings Christine Basta Marta R. Costa-jussá Noe Casas 16 189 0 18 Apr 2019
Gender Bias in Contextualized Word Embeddings Jieyu Zhao Tianlu Wang Mark Yatskar Ryan Cotterell Vicente Ordonez Kai-Wei Chang FaML 27 415 0 05 Apr 2019
Identifying and Reducing Gender Bias in Word-Level Language Models Shikha Bordia Samuel R. Bowman FaML 48 322 0 05 Apr 2019
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings Thomas Manzini Y. Lim Yulia Tsvetkov A. Black FaML 9 304 0 03 Apr 2019
Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence Navid Rekabsaz Robert West James Henderson Allan Hanbury 13 0 0 13 Dec 2018