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
Tweets
This paper has been referenced on Twitter 82 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 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 Evaluation Labs…
  • 2016
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…