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.
Authors: Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, Daniel Gildea (University of Rochester, Singapore University of Technology and Design, IBM)