Natural Language to Structured Query Generation via Meta-Learning

By Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong He. 2018

129 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “4% without using a structured approach (Dong and Lapata, 2018; Huang et al., 2018; Yu et al., 2018b).”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, background): “These datasets have been studied for decades in both the NLP community (Warren and Pereira, 1982; Popescu et al., 2003b, 2004; Li et al., 2006; Giordani and Moschitti, 2012; Wang et al., 2017; Iyer et al., 2017; Zhong et al., 2017; Xu et al., 2017; Yu et al., 2018; Huang et al., 2018; Wang et al., 2”
Zero-shot Text Classification With Generative Language Models (2019, background): “…translation in low resource languages (Gu et al., 2018), iteratively guiding policies with language (Co-Reyes et al., 2018) for instruction following (Branavan et al., 2009; Chen and Mooney, 2011), and generating WikiSQL-style structured queries from natural language queries (Huang et al., 2018).”
Meta-Learning in Neural Networks: A Survey (2020, background): “Many more tasks have since been tackled, including text classification [135], neural program induction [263] and synthesis [264], English to SQL program synthesis [265], text-based relationship graph extractor [266], machine translation [267], and quickly adapting to new personas in dialogue”
Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing (2019, methodology): “There also exist works to utilize multiple examples to guide the semantic parser (Hayati et al., 2018; Huang et al., 2018a), however, these approaches either use a heuristic way to exploit the retrieved logical form such as increasing the probability of actions (Hayati et al., 2018) or use a…”
Noisy Channel Language Model Prompting for Few-Shot Text Classification (2021, background): “…work in few-shot learning has used different approaches, including semi-supervised learning with data augmentation or consistency training (Miyato et al., 2017; Clark et al., 2018; Xie et al., 2020; Chen et al., 2020) and meta learning (Finn et al., 2017; Huang et al., 2018; Bansal et al., 2020).”
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems (2019, methodology): “Moreover, few-shot learning in natural language applications has been applied in semantic parsing (Huang et al., 2018), machine translation (Gu et al.”
Revisiting Meta-Learning as Supervised Learning (2020, background): “…2017; Bello et al., 2017), recommendation systems (Vartak et al., 2017), data augmentation (Ratner et al., 2017), natural language processing (Huang et al., 2018), architecture search (Elsken et al., 2018), continual learning (Riemer et al., 2019; Kaiser et al., 2017; Al-Shedivat et al.,…”
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning (2022, methodology): “MAML has been successfully implemented in various data-limited applications including medical image analysis (Maicas et al., 2018), language modelling (Huang et al., 2018), and object detection (Wang et al., 2020).”
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (2019, unknown): “…approaches achieve promising results (Dong and Lapata, 2016; Su and Yan, 2017; Iyer et al., 2017; Xu et al., 2017; Finegan-Dollak et al., 2018; Yu et al., 2018a; Huang et al., 2018; Dong and Lap-ata, 2018; Sun et al., 2018; Gur et al., 2018; Guo et al., 2018; Yavuz et al., 2018; Shi et al., 2018).”
Robust Text-to-SQL Generation with Execution-Guided Decoding (2018, background): “A large number of subsequent neural semantic parsing works included an evaluation on WikiSQL (Xu, Liu, and Song 2017; Huang et al. 2018; Yu et al. 2018; Wang et al. 2018; Dong and Lapata 2018).”
How to Train Your MAML to Excel in Few-Shot Classification (2021, methodology): “MAML has been applied in various scenarios, such as uncertainty estimation [32], robotics control [16, 113], neural translation [37], language generation [42], etc.”
Learning to Generalize from Sparse and Underspecified Rewards (2019, methodology): “, 2018), and semantic parsing by treating each query as a separate task (Huang et al., 2018).”
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization (2019, unknown): “0 PT-MAML (Huang et al., 2018) 63.”