Simple and effective data augmentation for compositional generalization

18 Jan 2024  ·  Yuekun Yao, Alexander Koller ·

Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models. In this paper, we show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization, but only if we sample from the right distribution. Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution, and greatly outperforms earlier methods that sampled from the training distribution. We further conduct experiments to investigate the reason why this happens and where the benefit of such data augmentation methods come from.

PDF Abstract
No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.