Natural Language to Structured Query Generation via Meta-Learning
This work addresses the challenge of handling diverse examples in natural language to SQL conversion, offering an incremental improvement over existing methods.
The paper tackles the problem of generating structured queries from natural language by proposing a meta-learning protocol that treats each example as a pseudo-task, leading to faster convergence and achieving 1.1%-5.4% absolute accuracy gains on the WikiSQL dataset.
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.