AMR-to-text Generation with Synchronous Node Replacement Grammar
2017-02-01ACL 2017Unverified0· sign in to hype
Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, Daniel Gildea
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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.