AMR Parsing as Sequence-to-Graph Transduction
Computation and Language
2019-06-25 v2
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).
Keywords
Cite
@article{arxiv.1905.08704,
title = {AMR Parsing as Sequence-to-Graph Transduction},
author = {Sheng Zhang and Xutai Ma and Kevin Duh and Benjamin Van Durme},
journal= {arXiv preprint arXiv:1905.08704},
year = {2019}
}
Comments
Accepted at ACL 2019