AMR Parsing as Sequence-to-Graph Transduction

@article{Zhang2019AMRPA,
  title={AMR Parsing as Sequence-to-Graph Transduction},
  author={Sheng Zhang and Xutai Ma and Kevin Duh and Benjamin Van Durme},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.08704}
}
  • Sheng Zhang, Xutai Ma, +1 author Benjamin Van Durme
  • Published 2019
  • Computer Science
  • ArXiv
  • 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). 

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 28 CITATIONS

    Broad-Coverage Semantic Parsing as Transduction

    VIEW 17 EXCERPTS
    CITES METHODS & BACKGROUND

    AMR Parsing via Graph-Sequence Iterative Inference

    VIEW 25 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Core Semantic First: A Top-down Approach for AMR Parsing

    VIEW 1 EXCERPT
    CITES BACKGROUND

    MRP 2019: Cross-Framework Meaning Representation Parsing

    VIEW 1 EXCERPT
    CITES METHODS

    FILTER CITATIONS BY YEAR

    2019
    2020

    CITATION STATISTICS

    • 7 Highly Influenced Citations

    • Averaged 14 Citations per year from 2019 through 2020

    References

    Publications referenced by this paper.