Natural Language to Structured Query Generation via Meta-Learning

Abstract

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.

arXiv commentin NAACL HLT 2018

Cited by in corpus (8)

• Learning to Generalize from Sparse and Underspecified Rewards
• Neural Language Generation: Formulation, Methods, and Evaluation
• Revisiting Meta-Learning as Supervised Learning
• DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks
• Set-to-Sequence Methods in Machine Learning: a Review
• Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
• KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers
• Learning to Learn Morphological Inflection for Resource-Poor Languages