Adversarial removal of demographic attributes revisited

Maria Barrett, Yova Kementchedjhieva, Yanai Elazar, Desmond Elliott, Anders Søgaard

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Scopus citations

Abstract

Elazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier on a held-out subsample of the data it was trained on. We revisit their experiments and conduct a series of follow-up experiments showing that, in fact, the diagnostic classifier generalizes poorly to both new in-domain samples and new domains, indicating that it relies on correlations specific to their particular data sample. We further show that a diagnostic classifier trained on the biased baseline neural network also does not generalize to new samples. In other words, the biases detected in Elazar and Goldberg (2018) seem restricted to their particular data sample, and would therefore not bias the decisions of the model on new samples, whether in-domain or out-of-domain. In light of this, we discuss better methodologies for detecting bias in our models.

Original languageEnglish
Title of host publicationEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics
Pages6330-6335
Number of pages6
ISBN (Electronic)9781950737901
StatePublished - 2019
Event2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, China
Duration: 3 Nov 20197 Nov 2019

Publication series

NameEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference

Conference

Conference2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Country/TerritoryChina
CityHong Kong
Period3/11/197/11/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Fingerprint

Dive into the research topics of 'Adversarial removal of demographic attributes revisited'. Together they form a unique fingerprint.

Cite this