Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

TL;DR

This paper introduces macro grammars and holistic triggering to accelerate semantic parsing training, achieving faster learning and improved accuracy on a question-answering dataset.

Contribution

It presents a novel online learning algorithm that uses macro grammars and holistic triggering to speed up semantic parser training and enhance accuracy.

Findings

Achieved 43.7% accuracy on WikiTableQuestions.

Realized an 11x speedup in training.

Improved state-of-the-art accuracy from 38.7% to 42.7%.

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%.