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
- ImageNet classification with deep convolutional neural networks
- Long Short-Term Memory
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Attention Is All You Need
- Sequence to Sequence Learning with Neural Networks
- ASPECTS OF THE THEORY OF SYNTAX
- Distributed Representations of Words and Phrases and their Compositionality
- Deep Contextualized Word Representations
- mixup: Beyond Empirical Risk Minimization
- The Proper Treatment of Quantification in Ordinary English