Corpus ID: 221819216

Multitask Pointer Network for Multi-Representational Parsing

@article{FernndezGonzlez2020MultitaskPN,
  title={Multitask Pointer Network for Multi-Representational Parsing},
  author={Daniel Fern{\'a}ndez-Gonz{\'a}lez and Carlos G'omez-Rodr'iguez},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.09730}
}
  • Daniel Fernández-González, Carlos G'omez-Rodr'iguez
  • Published 2020
  • Computer Science
  • ArXiv
  • We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 65 REFERENCES
    Discontinuous Constituent Parsing with Pointer Networks
    • 6
    • PDF
    Parsing as Reduction
    • 43
    • PDF
    Neural Probabilistic Model for Non-projective MST Parsing
    • 30
    • PDF
    Two Local Models for Neural Constituent Parsing
    • 15
    • PDF
    Sequence Labeling Parsing by Learning Across Representations
    • 9
    • PDF
    Left-to-Right Dependency Parsing with Pointer Networks
    • 25
    • PDF
    A Minimal Span-Based Neural Constituency Parser
    • 107
    • PDF
    Constituency Parsing with a Self-Attentive Encoder
    • 191
    • PDF