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

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.

arXiv commentEMNLP'18

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Synthetic and Natural Noise Both Break Neural Machine Translation
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Language to Logical Form with Neural Attention
• Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
• Universal Semantic Parsing
• Sentence-State LSTM for Text Representation
• D2KE: From Distance to Kernel and Embedding
• Word Mover's Embedding: From Word2Vec to Document Embedding
• Cross-domain Semantic Parsing via Paraphrasing

Cited by in corpus (12)

• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Deep Iterative and Adaptive Learning for Graph Neural Networks
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
• TreeGen: A Tree-Based Transformer Architecture for Code Generation
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
• Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
• Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
• DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums