- Keywords: compositional generalization, data augmentation, language processing, sequence models, generative modeling
- Abstract: Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data—particularly to rare or unseen subsequences. Past work has found symbolic scaffolding (e.g. grammars or automata) essential in these settings. We describe R&R, a learned data augmentation scheme that enables a large category of compositional generalizations without appeal to latent symbolic structure. R&R has two components: recombination of original training examples via a prototype-based generative model and resampling of generated examples to encourage extrapolation. Training an ordinary neural sequence model on a dataset augmented with recombined and resampled examples significantly improves generalization in two language processing problems—instruction following (SCAN) and morphological analysis (SIGMORPHON 2018)—where R&R enables learning of new constructions and tenses from as few as eight initial examples.
- One-sentence Summary: This paper investigates a data augmentation procedure based on two weaker principles: recombination and resampling, and finds that it is sufficient to induce many of the compositional generalizations studied in previous work.
- Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
- Supplementary Material: zip