A Graph-to-Sequence Model for AMR-to-Text Generation
arXiv:1805.02473
Abstract
The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus faces challenges with large graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.
arXiv commentACL 2018 camera-ready, Proceedings of ACL 2018 with updated performance
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Loopy Belief Propagation for Approximate Inference: An Empirical Study
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Modeling Coverage for Neural Machine Translation
- Pointing the Unknown Words
- AMR-to-text Generation with Synchronous Node Replacement Grammar
Cited by in corpus (17)
- Graph Neural Networks: A Review of Methods and Applications
- Recent Advances and Applications of Deep Learning Methods in Materials Science
- Describing a Knowledge Base
- Multi-hop Question Generation with Graph Convolutional Network
- Graph Transformer for Graph-to-Sequence Learning
- One-Shot Relational Learning for Knowledge Graphs
- Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
- Recursive Graphical Neural Networks for Text Classification
- Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
- Graph-based Neural Sentence Ordering
- Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph
- SQL-to-Text Generation with Graph-to-Sequence Model
- Lattice CNNs for Matching Based Chinese Question Answering
- Compositional Language Understanding with Text-based Relational Reasoning
- Semantic-Based Self-Critical Training For Question Generation
- Online Back-Parsing for AMR-to-Text Generation
- EAT: a simple and versatile semantic representation format for multi-purpose NLP