Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

TL;DR

This paper introduces a graph-to-sequence model that leverages rich syntactic information, including dependency and constituency graphs, to improve semantic parsing accuracy and robustness over traditional sequence-based models.

Contribution

The paper proposes using a syntactic graph to encode multiple types of syntactic information and employs a graph-to-sequence model for semantic parsing, enhancing performance and robustness.

Findings

Comparable to state-of-the-art on benchmark datasets

Improved robustness against adversarial examples

Effective encoding of dependency and constituency information

Abstract

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.