Good-Enough Compositional Data Augmentation

Jacob Andreas · Annual Meeting of the Association for Computational Linguistics (ACL) · 2020

We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models.Under this protocol, synthetic training examples are constructed by taking real training examples and replacing (possibly discontinuous) fragments with other fragments that appear in at least one similar environment.The protocol is model-agnostic and useful for a variety of tasks.Applied to neural sequence-to-sequence models, it reduces error rate by as much as 87% on diagnostic tasks from the SCAN dataset and 16% on a semantic parsing task.Applied to n-gram language models, it reduces perplexity by roughly 1% on small corpora in several languages.

Cited by 175 works. doi:10.18653/v1/2020.acl-main.676 Open-access PDF

Authors

References