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

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed