SQL-to-Text Generation with Graph-to-Sequence Model
arXiv:1809.05255
Abstract
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query. In this paper, we first introduce a strategy to represent the SQL query as a directed graph and then employ a graph-to-sequence model to encode the global structure information into node embeddings. This model can effectively learn the correlation between the SQL query pattern and its interpretation. Experimental results on the WikiSQL dataset and Stackoverflow dataset show that our model significantly outperforms the Seq2Seq and Tree2Seq baselines, achieving the state-of-the-art performance.
arXiv commentEMNLP18, Accepted
References in corpus (8)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Convolutional Neural Networks for Sentence Classification
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Tree-to-Sequence Attentional Neural Machine Translation
- A Graph-to-Sequence Model for AMR-to-Text Generation
- D2KE: From Distance to Kernel and Embedding
Cited by in corpus (5)
- Deep Iterative and Adaptive Learning for Graph Neural Networks
- GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
- 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
- Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model