Approximation-Aware Dependency Parsing by Belief Propagation

@article{Gormley2015ApproximationAwareDP,
  title={Approximation-Aware Dependency Parsing by Belief Propagation},
  author={Matthew R. Gormley and Mark Dredze and Jason Eisner},
  journal={Transactions of the Association for Computational Linguistics},
  year={2015},
  volume={3},
  pages={489-501}
}
  • Matthew R. Gormley, Mark Dredze, Jason Eisner
  • Published in
    Transactions of the…
    2015
  • Computer Science
  • We show how to train the fast dependency parser of Smith and Eisner (2008) for improved accuracy. This parser can consider higher-order interactions among edges while retaining O(n3) runtime. It outputs the parse with maximum expected recall—but for speed, this expectation is taken under a posterior distribution that is constructed only approximately, using loopy belief propagation through structured factors. We show how to adjust the model parameters to compensate for the errors introduced by… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 18 CITATIONS

    Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks

    VIEW 1 EXCERPT
    CITES METHODS

    DyNet: The Dynamic Neural Network Toolkit

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES

    CoNLL-X Shared Task on Multilingual Dependency Parsing

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Experiments with a Higher-Order Projective Dependency Parser

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL