Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing

TL;DR

This paper introduces Sequence-to-Action, an end-to-end neural semantic parsing method that generates semantic graphs directly from sentences, combining graph-based meaning representation with neural sequence modeling for improved accuracy.

Contribution

It presents a novel neural approach that models semantic parsing as semantic graph generation, integrating knowledge base alignment with neural sequence prediction.

Findings

Achieves state-of-the-art results on OVERNIGHT dataset

Performs competitively on GEO and ATIS datasets

Demonstrates effective end-to-end semantic graph generation

Abstract

This paper proposes a neural semantic parsing approach -- Sequence-to-Action, which models semantic parsing as an end-to-end semantic graph generation process. Our method simultaneously leverages the advantages from two recent promising directions of semantic parsing. Firstly, our model uses a semantic graph to represent the meaning of a sentence, which has a tight-coupling with knowledge bases. Secondly, by leveraging the powerful representation learning and prediction ability of neural network models, we propose a RNN model which can effectively map sentences to action sequences for semantic graph generation. Experiments show that our method achieves state-of-the-art performance on OVERNIGHT dataset and gets competitive performance on GEO and ATIS datasets.