Imitation Learning of Agenda-based Semantic Parsers
Published
2015-11-20
Jonathan Berant
,
Percy Liang
Jonathan Berant
Stanford University
Percy Liang
Stanford University
Abstract
Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.
PDF (presented at NAACL 2016)