Adversarial Removal of Demographic Attributes from Text Data

@inproceedings{Elazar2018AdversarialRO,
  title={Adversarial Removal of Demographic Attributes from Text Data},
  author={Yanai Elazar and Yoav Goldberg},
  booktitle={EMNLP},
  year={2018}
}
Highlight Information
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. [...] Key Result Our main conclusion is a cautionary one: do not rely on the adversarial training to achieve invariant representation to sensitive features.Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 43 CITATIONS

On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference

VIEW 3 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Mitigating Unwanted Biases with Adversarial Learning

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Controllable Invariance through Adversarial Feature Learning

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Overview of the 4th author profiling task at pan 2016: cross-genre evaluations

  • Francisco Rangel, Paolo Rosso, +3 authors Benno Stein.
  • Working Notes Papers of the CLEF 2016 Evaluation
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Unsupervised Domain Adaptation by Backpropagation

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 3 EXCERPTS

Demographic Parity. A predictor f satisfies demographic parity if f and z are independent

  • Hardt
  • 2018