Text Augmentation in a Multi-Task View

Jason Wei, Chengyu Huang, Shiqi Xu, Soroush Vosoughi


Abstract
Traditional data augmentation aims to increase the coverage of the input distribution by generating augmented examples that strongly resemble original samples in an online fashion where augmented examples dominate training. In this paper, we propose an alternative perspective—a multi-task view (MTV) of data augmentation—in which the primary task trains on original examples and the auxiliary task trains on augmented examples. In MTV data augmentation, both original and augmented samples are weighted substantively during training, relaxing the constraint that augmented examples must resemble original data and thereby allowing us to apply stronger augmentation functions. In empirical experiments using four common data augmentation techniques on three benchmark text classification datasets, we find that using the MTV leads to higher and more robust performance than traditional augmentation.
Anthology ID:
2021.eacl-main.252
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2888–2894
Language:
URL:
https://aclanthology.org/2021.eacl-main.252
DOI:
10.18653/v1/2021.eacl-main.252
Bibkey:
Cite (ACL):
Jason Wei, Chengyu Huang, Shiqi Xu, and Soroush Vosoughi. 2021. Text Augmentation in a Multi-Task View. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2888–2894, Online. Association for Computational Linguistics.
Cite (Informal):
Text Augmentation in a Multi-Task View (Wei et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.252.pdf