AMR Parsing as Sequence-to-Graph Transduction

Abstract

We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it can be effectively trained with limited amounts of labeled AMR data. Our experimental results outperform all previously reported SMATCH scores, on both AMR 2.0 (76.3% F1 on LDC2017T10) and AMR 1.0 (70.2% F1 on LDC2014T12).

Accepted at ACL 2019

References in corpus (3)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Pointer Sentinel Mixture Models
• Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

Cited by in corpus (1)

• Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning