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.
@article{arxiv.1803.02400,
title = {Natural Language to Structured Query Generation via Meta-Learning},
author = {Po-Sen Huang and Chenglong Wang and Rishabh Singh and Wen-tau Yih and Xiaodong He},
journal= {arXiv preprint arXiv:1803.02400},
year = {2018}
}