Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
This work addresses efficiency and accuracy challenges in semantic parsing for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the problem of learning semantic parsers from denotations by proposing an online learning algorithm that uses macro grammars and holistic triggering to speed up search over logical forms, achieving an 11x speedup and improving accuracy from 38.7% to 43.7% on the WikiTableQuestions dataset.
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%.