The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing

2017/04/07 by van Noord, Rik, Bos, Johan
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1704.02156

Abstract

We evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval-2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and POS-tagging we gain major improvements in performance compared to a baseline character-level model. Although we improve on previous character-based neural semantic parsing models, the overall accuracy is still lower than a state-of-the-art AMR parser. An ensemble combining our neural semantic parser with an existing, traditional parser, yields a small gain in performance.

Related

• Neural Semantic Parsing by Character-based Translation: Experiments with\n Abstract Meaning Representations
• Neural AMR: Sequence-to-Sequence Models for Parsing and Generation
• Improving AMR Parsing with Sequence-to-Sequence Pre-training
• An Incremental Parser for Abstract Meaning Representation
• RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and\n Character-Level Neural Translation on AMR Parsing Accuracy