Detecting Independent Pronoun Bias with Partially-Synthetic Data Generation

Robert Munro, Alex (Carmen) Morrison

Interpretability and Analysis of Models for NLP Short Paper

Gather-1I: Nov 17, Gather-1I: Nov 17 (02:00-04:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in a separate window.

Abstract: We report that state-of-the-art parsers consistently failed to identify “hers” and “theirs” as pronouns but identified the masculine equivalent “his”. We find that the same biases exist in recent language models like BERT. While some of the bias comes from known sources, like training data with gender imbalances, we find that the bias is _amplified_ in the language models and that linguistic differences between English pronouns that are not inherently biased can become biases in some machine learning models. We introduce a new technique for measuring bias in models, using Bayesian approximations to generate partially-synthetic data from the model itself.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EMNLP2020

Similar Papers