Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

Abstract

We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed logical forms; and (2) an entity embedding and linking module that identifies entity mentions while generalizing across tables. We also introduce a novel method for training our neural model with question-answer supervision. On the WIKITABLEQUESTIONS data set, our parser achieves a state-of-theart accuracy of 43.3% for a single model and 45.9% for a 5-model ensemble, improving on the best prior score of 38.7% set by a 15-model ensemble. These results suggest that type constraints and entity linking are valuable components to incorporate in neural semantic parsers.

6 Figures and Tables

Cite this paper

@inproceedings{Krishnamurthy2017NeuralSP, title={Neural Semantic Parsing with Type Constraints for Semi-Structured Tables}, author={Jayant Krishnamurthy and Pradeep Dasigi and Matthew Gardner}, booktitle={EMNLP}, year={2017} }