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

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.

arXiv commentAccepted as ACL 2018 long paper

References in corpus (1)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

Cited by in corpus (13)

• 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
• Building a Neural Semantic Parser from a Domain Ontology
• Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
• AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
• Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
• Semantic Parsing with Dual Learning
• Few-Shot Semantic Parsing for New Predicates
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
• From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding
• On Robustness of Neural Semantic Parsers
• LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network
• Semantic Graph Parsing with Recurrent Neural Network DAG Grammars