C2L: Causally Contrastive Learning for Robust Text Classification

Seungtaek Choi, Myeongho Jeong, Hojae Han, Seung Won Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Despite the super-human accuracy of recent deep models in NLP tasks, their robustness is reportedly limited due to their reliance on spurious patterns. We thus aim to leverage contrastive learning and counterfactual augmentation for robustness. For augmentation, existing work either requires humans to add counterfactuals to the dataset or machines to automatically matches near-counterfactuals already in the dataset. Unlike existing augmentation is affected by spurious correlations, ours, by synthesizing "a set"of counterfactuals, and making a collective decision on the distribution of predictions on this set, can robustly supervise the causality of each term. Our empirical results show that our approach, by collective decisions, is less sensitive to task model bias of attribution-based synthesis, and thus achieves significant improvements, in diverse dimensions: 1) counterfactual robustness, 2) cross-domain generalization, and 3) generalization from scarce data.

Original languageEnglish
Title of host publicationAAAI-22 Technical Tracks 10
PublisherAssociation for the Advancement of Artificial Intelligence
Pages10526-10534
Number of pages9
ISBN (Electronic)1577358767, 9781577358763
Publication statusPublished - 2022 Jun 30
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: 2022 Feb 222022 Mar 1

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume36

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period22/2/2222/3/1

Bibliographical note

Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'C2L: Causally Contrastive Learning for Robust Text Classification'. Together they form a unique fingerprint.

Cite this