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 outperfonn all previously reported Smatch scores, on both AMR 2.0 (76.3% Fl on LDC2017T10) and AMR 1.0 (70.2% Fl on LDC2014T12).
展开▼
