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}
}
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in—and can be recovered from—the intermediate representations learned by text-based neural classifiers. The implication is that decisions of classifiers trained on textual data are not agnostic to—and likely condition on— demographic attributes. When attempting to remove such demographic… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 41 references

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

  • Francisco Rangel, Paolo Rosso, Ben Verhoeven, Walter Daelemans, Martin Potthast, Benno Stein.
  • Working Notes Papers of the CLEF 2016 Evaluation
  • 2016
Highly Influential
4 Excerpts

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

  • Hardt
  • 2018

Similar Papers

Loading similar papers…