Increasing Robustness to Spurious Correlations using Forgettable Examples

Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been shown to increase the out-of-distribution generalization of...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-02
Main Authors: Yaghoobzadeh, Yadollah, Soroush Mehri, Tachet, Remi, Hazen, T J, Sordoni, Alessandro
Format: Article
Language:English
Subjects:
Inference
Model testing
Natural language
Robustness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the majority of data points, have been shown to increase the out-of-distribution generalization of pre-trained language models. In this paper, we first propose using example forgetting to find minority examples without prior knowledge of the spurious correlations present in the dataset. Forgettable examples are instances either learned and then forgotten during training or never learned. We empirically show how these examples are related to minorities in our training sets. Then, we introduce a new approach to robustify models by fine-tuning our models twice, first on the full training data and second on the minorities only. We obtain substantial improvements in out-of-distribution generalization when applying our approach to the MNLI, QQP, and FEVER datasets.
ISSN:2331-8422