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.
@article{arxiv.1702.00500,
title = {AMR-to-text Generation with Synchronous Node Replacement Grammar},
author = {Linfeng Song and Xiaochang Peng and Yue Zhang and Zhiguo Wang and Daniel Gildea},
journal= {arXiv preprint arXiv:1702.00500},
year = {2017}
}