Rational Recurrences

@article{Peng2018RationalR,
  title={Rational Recurrences},
  author={Hao Peng and Roy Schwartz and Sam Thomson and Noah A. Smith},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.09357}
}
  • Hao Peng, Roy Schwartz, +1 author Noah A. Smith
  • Published 2018
  • Computer Science
  • ArXiv
  • Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. [...] Key Method We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forward calculation of a finite set of WFSAs. We show that several recent neural models use rational recurrences. Our analysis provides a fresh view of these models and…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 17 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 70 REFERENCES

    Strongly-Typed Recurrent Neural Networks

    VIEW 3 EXCERPTS

    Learning Longer Memory in Recurrent Neural Networks

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    A Primer on Neural Network Models for Natural Language Processing

    • Yoav Goldberg
    • Computer Science, Mathematics
    • J. Artif. Intell. Res.
    • 2016
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Attention is All you Need

    VIEW 1 EXCERPT