Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

Abstract

Neural semantic parsing has achieved impressive results in recent years, yet its success relies on the availability of large amounts of supervised data. Our goal is to learn a neural semantic parser when only prior knowledge about a limited number of simple rules is available, without access to either annotated programs or execution results. Our approach is initialized by rules, and improved in a back-translation paradigm using generated question-program pairs from the semantic parser and the question generator. A phrase table with frequent mapping patterns is automatically derived, also updated as training progresses, to measure the quality of generated instances. We train the model with model-agnostic meta-learning to guarantee the accuracy and stability on examples covered by rules, and meanwhile acquire the versatility to generalize well on examples uncovered by rules. Results on three benchmark datasets with different domains and programs show that our approach incrementally improves the accuracy. On WikiSQL, our best model is comparable to the SOTA system learned from denotations.

References in corpus (13)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Large-scale Simple Question Answering with Memory Networks
• Machine Comprehension Using Match-LSTM and Answer Pointer
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Phrase-Based & Neural Unsupervised Machine Translation
• Compositional Semantic Parsing on Semi-Structured Tables
• Learning to Generalize from Sparse and Underspecified Rewards
• IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
• Natural Language to Structured Query Generation via Meta-Learning
• Unsupervised Neural Machine Translation with SMT as Posterior Regularization
• Building a Neural Semantic Parser from a Domain Ontology
• Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations

Cited by in corpus (3)

• Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing
• Meta-Learning for Domain Generalization in Semantic Parsing
• Few-Shot Semantic Parsing for New Predicates