AMR Parsing as Sequence-to-Graph Transduction

ACL 2019  ·  Sheng Zhang, Xutai Ma, Kevin Duh, Benjamin Van Durme ·

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).

PDF Abstract ACL 2019 PDF ACL 2019 Abstract

Datasets

LDC2017T10

Results from the Paper
Edit

 Ranked #1 on AMR Parsing on LDC2014T12:

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
AMR Parsing LDC2014T12 Two-stage Sequence-to-Graph Transducer F1 Full 70.2 # 5
Compare
AMR Parsing LDC2014T12: Sequence-to-Graph Transduction F1 Newswire 0.75 # 1
Compare
F1 Full 0.70 # 1
Compare
AMR Parsing LDC2017T10 Sequence-to-Graph Transduction Smatch 76.3 # 21
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy