Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

Abstract

To learn a semantic parser from denotations, a learning algorithm must search over a combinatorially large space of logical forms for ones consistent with the annotated denotations. We propose a new online learning algorithm that searches faster as training progresses. The two key ideas are using macro grammars to cache the abstract patterns of useful logical forms found thus far, and holistic triggering to efficiently retrieve the most relevant patterns based on sentence similarity. On the WikiTableQuestions dataset, we first expand the search space of an existing model to improve the state-of-the-art accuracy from 38.7% to 42.7%, and then use macro grammars and holistic triggering to achieve an 11x speedup and an accuracy of 43.7%.

EMNLP 2017

References in corpus (7)

• Lambda Dependency-Based Compositional Semantics
• Language to Logical Form with Neural Attention
• Compositional Semantic Parsing on Semi-Structured Tables
• Learning Dependency-Based Compositional Semantics
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Cornell SPF: Cornell Semantic Parsing Framework
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables

Cited by in corpus (3)

• Learning to Generalize from Sparse and Underspecified Rewards
• Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks
• Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering