Natural Language to Structured Query Generation via Meta-Learning

  • Po-Sen Huang ,
  • Chenglong Wang ,
  • Rishabh Singh ,
  • Wen-tau Yih ,
  • Xiaodong He

NAACL HLT 2018 |

Publication

In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats each example as a unique pseudo-task, by reducing the original learning problem to a few-shot meta-learning scenario with the help of a domain-dependent relevance function. When evaluated on the WikiSQL dataset, our approach leads to faster convergence and achieves 1.1%–5.4% absolute accuracy gains over the non-meta-learning counterparts.