Byungchul Tak, Shu Tao, et al.
IC2E 2016
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.
Byungchul Tak, Shu Tao, et al.
IC2E 2016
Kevin Gu, Eva Tuecke, et al.
ICML 2024
Zongyuan Ge, Sergey Demyanov, et al.
BMVC 2017
Kristjan Greenewald, Yuancheng Yu, et al.
NeurIPS 2024