CLFeb 1, 2017
AMR-to-text Generation with Synchronous Node Replacement Grammar
arXiv:1702.00500v455 citations
Originality Incremental advance
AI Analysis
This addresses the problem of generating natural language text from Abstract Meaning Representation graphs for NLP applications, with incremental improvements.
The paper tackled AMR-to-text generation by using synchronous node replacement grammar, achieving a state-of-the-art BLEU score of 25.62 on the SemEval-2016 Task 8 benchmark.
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.