Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
This work addresses the challenge of incorporating rich syntactic information for semantic parsing, which is incremental as it builds on existing graph-to-sequence models to enhance performance and robustness in natural language processing tasks.
The paper tackled the problem of neural semantic parsers neglecting valuable syntactic information like dependency and constituency features by proposing a syntactic graph representation and a graph-to-sequence model, achieving comparable state-of-the-art results on benchmark datasets such as Jobs640, ATIS, and Geo880 and improved robustness on adversarial examples.
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.