Better, Faster, Stronger Sequence Tagging Constituent Parsers

@article{Vilares2019BetterFS,
  title={Better, Faster, Stronger Sequence Tagging Constituent Parsers},
  author={David Vilares and Mostafa Abdou and Anders S{\o}gaard},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.10985}
}
  • David Vilares, Mostafa Abdou, Anders Søgaard
  • Published 2019
  • Computer Science
  • ArXiv
  • Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 11 CITATIONS

    Towards Making a Dependency Parser See

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    A Span-based Linearization for Constituent Trees

    VIEW 1 EXCERPT
    CITES METHODS

    Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference

    VIEW 3 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED