A Probabilistic Generative Grammar for Semantic Parsing

Abulhair Saparov, Vijay Saraswat, Tom Mitchell


Abstract
We present a generative model of natural language sentences and demonstrate its application to semantic parsing. In the generative process, a logical form sampled from a prior, and conditioned on this logical form, a grammar probabilistically generates the output sentence. Grammar induction using MCMC is applied to learn the grammar given a set of labeled sentences with corresponding logical forms. We develop a semantic parser that finds the logical form with the highest posterior probability exactly. We obtain strong results on the GeoQuery dataset and achieve state-of-the-art F1 on Jobs.
Anthology ID:
K17-1026
Volume:
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Roger Levy, Lucia Specia
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
248–259
Language:
URL:
https://aclanthology.org/K17-1026
DOI:
10.18653/v1/K17-1026
Bibkey:
Cite (ACL):
Abulhair Saparov, Vijay Saraswat, and Tom Mitchell. 2017. A Probabilistic Generative Grammar for Semantic Parsing. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 248–259, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
A Probabilistic Generative Grammar for Semantic Parsing (Saparov et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-1026.pdf
Code
 asaparov/parser +  additional community code