Understanding the Origins of Bias in Word Embeddings

Characterizations of an empirical influence function for detecting influential cases in regression

Cook, R. and Weisberg, S · 1980

Earlier work this paper cites.

Measuring individual differences in implicit cognition: The implicit association test

Greenwald, A. G., McGhee, D. E., and Schwartz, J. L. K · 1998

Earlier work this paper cites.

The new york times annotated corpus, 2008

Sandhaus, E · 2008

Earlier work this paper cites.

Fairness through awareness

Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R · 2012

Earlier work this paper cites.

Explaining robot actions

Lomas, M., Chevalier, R., II, E. C., Garrett, R., Hoare, J., and Kopack, M · 2012

Earlier work this paper cites.

Linguistic regularities in continuous space word representations

Mikolov, T., t. Yih, W., and Zweig, G · 2013

Earlier work this paper cites.

Discrimination in online ad delivery

Sweeney, L · 2013

Earlier work this paper cites.

Glove: Global vectors for word representation

Pennington, J., Socher, R., and Manning, C · 2014

Earlier work this paper cites.

Improving Distributional Similarity with Lessons Learned from Word Embeddings

Levy, O., Goldberg, Y., and Dagan, I · 2015

Cited alongside, same era.

Machine bias: There’s software used across the country to predict future criminals. and it’s biased against blacks

Angwin, J., Larson, J., Mattu, S., and Kirchner, L · 2016

Cited alongside, same era.

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

Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., and Kalai, A · 2016

Cited alongside, same era.

Equality of opportunity in supervised learning

Hardt, M., Price, E., Srebro, N., et al · 2016

Cited alongside, same era.

Generating visual explanations

Hendricks, L., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., and Darrell, T · 2016

Cited alongside, same era.

Inherent trade-offs in the fair determination of risk scores

Second-order stochastic optimization for machine learning in linear time

Agarwal, N., Bullins, B., and Hazan, E · 2017

Later among the works it cites.

Semantics derived automatically from language corpora contain human-like biases

Caliskan, A., Bryson, J. J., and Narayanan, A · 2017

Later among the works it cites.

Understanding Black-box Predictions via Influence Functions

Koh, P. W. and Liang, P · 2017

Later among the works it cites.

Men also like shopping: Reducing gender bias amplification using corpus-level constraints

Zhao, J., Wang, T., Yatskar, M., Ordonez, V., and Chang, K.-W · 2017

Later among the works it cites.

Evaluating the stability of embedding-based word similarities

Antoniak, M. and Mimno, D · 2018

Closest in time.

Simplewiki:database download, 2018

Wikimedia · 2018

Closest in time.