Natural Language to Structured Query Generation via Meta-Learning

2018/03/02 by Po-Sen Huang, Huang, Po-Sen, Chenglong Wang +7 · 1 citation
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1803.02400

openalex publication_date 2018/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Neural Language Generation: Formulation, Methods, and Evaluation

Related

• Improved Compositional Generalization by Generating Demonstrations for Meta-Learning
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Meta Learning for Natural Language Processing: A Survey
• Meta-training with Demonstration Retrieval for Efficient Few-shot Learning