Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information

Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them

Original

Hila Gonen and Yoav Goldberg. 2019 · 1903

Earlier work this paper cites.

Black is to criminal as caucasian is to police: Detecting and removing multiclass bias in word embeddings

Original

Thomas Manzini, Yao Chong Lim, Yulia Tsvetkov, and Alan W Black. 2019 · 1904

Earlier work this paper cites.

Understanding undesirable word embedding associations

Original

Kawin Ethayarajh, David Duvenaud, and Graeme Hirst. 2019 · 1908

Earlier work this paper cites.

Placing search in context: The concept revisited

Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Eytan Ruppin. 2001 · 2001

Earlier work this paper cites.

Latent semantic analysis

Susan T Dumais. 2004 · 2004

Earlier work this paper cites.

Null it out: Guarding protected attributes by iterative nullspace projection

Original

Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, and Yoav Goldberg. 2020 · 2004

Earlier work this paper cites.

Large-scale learning of word relatedness with constraints

Guy Halawi, Gideon Dror, Evgeniy Gabrilovich, and Yehuda Koren. 2012 · 2012

Earlier work this paper cites.

Censoring representations with an adversary

Original

Harrison Edwards and Amos Storkey. 2015 · 2015

Earlier work this paper cites.

Simlex-999: Evaluating semantic models with (genuine) similarity estimation

Felix Hill, Roi Reichart, and Anna Korhonen. 2015 · 2015

Earlier work this paper cites.

Demographic dialectal variation in social media: A case study of african-american english

Original

Su Lin Blodgett, Lisa Green, and Brendan O’Connor. 2016 · 2016

Earlier work this paper cites.

Man is to computer programmer as woman is to homemaker? debiasing word embeddings

Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016 · 2016

Cited alongside, same era.

Equality of opportunity in supervised learning

Moritz Hardt, Eric Price, and Nati Srebro. 2016 · 2016

Cited alongside, same era.

Fasttext. zip: Compressing text classification models

Original

Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, and Tomas Mikolov. 2016 · 2016

Cited alongside, same era.

Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm

Original

Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, and Sune Lehmann. 2017 · 2017

Cited alongside, same era.

Cleaning the null space: A privacy mechanism for predictors

Ke Xu, Tongyi Cao, Swair Shah, Crystal Maung, and Haim Schweitzer. 2017 · 2017

Cited alongside, same era.

Learning gender-neutral word embeddings

Original

Jieyu Zhao, Yichao Zhou, Zeyu Li, Wei Wang, and Kai-Wei Chang. 2018 · 2018

Later among the works it cites.

Adversarial removal of demographic attributes revisited

Maria Barrett, Yova Kementchedjhieva, Yanai Elazar, Desmond Elliott, and Anders Søgaard. 2019 · 2019

Later among the works it cites.

Bias in bios: A case study of semantic representation bias in a high-stakes setting

Maria De-Arteaga, Alexey Romanov, Hanna Wallach, Jennifer Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Geyik, Krishnaram Kenthapadi, and Adam Tauman Kalai. 2019 · 2019

Later among the works it cites.

Diverse adversaries for mitigating bias in training

Xudong Han, Timothy Baldwin, and Trevor Cohn. 2021 · 2021

Later among the works it cites.

Learning disentangled textual representations via statistical measures of similarity

Original

Pierre Colombo, Guillaume Staerman, Nathan Noiry, and Pablo Piantanida. 2022 · 2022