SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness

Nathan Ng, Kyunghyun Cho, Marzyeh Ghassemi


Abstract
Models that perform well on a training domain often fail to generalize to out-of-domain (OOD) examples. Data augmentation is a common method used to prevent overfitting and improve OOD generalization. However, in natural language, it is difficult to generate new examples that stay on the underlying data manifold. We introduce SSMBA, a data augmentation method for generating synthetic training examples by using a pair of corruption and reconstruction functions to move randomly on a data manifold. We investigate the use of SSMBA in the natural language domain, leveraging the manifold assumption to reconstruct corrupted text with masked language models. In experiments on robustness benchmarks across 3 tasks and 9 datasets, SSMBA consistently outperforms existing data augmentation methods and baseline models on both in-domain and OOD data, achieving gains of 0.8% on OOD Amazon reviews, 1.8% accuracy on OOD MNLI, and 1.4 BLEU on in-domain IWSLT14 German-English.
Anthology ID:
2020.emnlp-main.97
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1268–1283
Language:
URL:
https://aclanthology.org/2020.emnlp-main.97
DOI:
10.18653/v1/2020.emnlp-main.97
Bibkey:
Cite (ACL):
Nathan Ng, Kyunghyun Cho, and Marzyeh Ghassemi. 2020. SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1268–1283, Online. Association for Computational Linguistics.
Cite (Informal):
SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness (Ng et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.97.pdf
Video:
 https://slideslive.com/38938909
Code
 nng555/ssmba
Data
ANLIIMDb Movie ReviewsMultiNLISST