期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：2888-2894
DOI：10.18653/v1/2021.eacl-main.252
语种：English
出版社：ACL Anthology
摘要：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.
