Abulhair Saparov
2017
A Probabilistic Generative Grammar for Semantic Parsing
Abulhair Saparov
|
Vijay Saraswat
|
Tom Mitchell
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
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.
Search