AMR-to-text Generation with Synchronous Node Replacement Grammar

Abstract

This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar. During training, graph-to-string rules are learned using a heuristic extraction algorithm. At test time, a graph transducer is applied to collapse input AMRs and generate output sentences. Evaluated on SemEval-2016 Task 8, our method gives a BLEU score of 25.62, which is the best reported so far.

arXiv commentcamera-ready version of ACL 2017

References in corpus (2)

• Addressing the Data Sparsity Issue in Neural AMR Parsing
• AMR-to-text generation as a Traveling Salesman Problem

Cited by in corpus (7)

• Abstract Meaning Representation for Multi-Document Summarization
• Graph Transformer for Graph-to-Sequence Learning
• A Graph-to-Sequence Model for AMR-to-Text Generation
• Graph-to-Sequence Learning using Gated Graph Neural Networks
• Transition-Based Generation from Abstract Meaning Representations
• Online Back-Parsing for AMR-to-Text Generation
• Understanding in Artificial Intelligence