Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

Yuchen Zhang, Panupong Pasupat, Percy Liang


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%.
Anthology ID:
D17-1125
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1214–1223
Language:
URL:
https://aclanthology.org/D17-1125
DOI:
10.18653/v1/D17-1125
Bibkey:
Cite (ACL):
Yuchen Zhang, Panupong Pasupat, and Percy Liang. 2017. Macro Grammars and Holistic Triggering for Efficient Semantic Parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1214–1223, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Macro Grammars and Holistic Triggering for Efficient Semantic Parsing (Zhang et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1125.pdf
Attachment:
 D17-1125.Attachment.zip
Code
 percyliang/sempre +  additional community code