NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation
Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha Swayamdipta
Abstract
While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing approaches for producing counterfactuals, manual or automated, rely on small perturbations via minimal edits, resulting in simplistic changes. We introduce NeuroCounterfactuals, designed as loose counterfactuals, allowing for larger edits which result in naturalistic generations containing linguistic diversity, while still bearing similarity to the original document. Our novel generative approach bridges the benefits of constrained decoding, with those of language model adaptation for sentiment steering. Training data augmentation with our generations results in both in-domain and out-of-domain improvements for sentiment classification, outperforming even manually curated counterfactuals, under select settings. We further present detailed analyses to show the advantages of NeuroCounterfactuals over approaches involving simple, minimal edits.- Anthology ID:
- 2022.findings-emnlp.371
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5056–5072
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.371
- DOI:
- 10.18653/v1/2022.findings-emnlp.371
- Cite (ACL):
- Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, and Swabha Swayamdipta. 2022. NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5056–5072, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation (Howard et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.findings-emnlp.371.pdf