Stack-propagation: Improved Representation Learning for Syntax

@article{Zhang2016StackpropagationIR,
  title={Stack-propagation: Improved Representation Learning for Syntax},
  author={Y. Zhang and D. Weiss},
  journal={ArXiv},
  year={2016},
  volume={abs/1603.06598}
}
  • Y. Zhang, D. Weiss
  • Published 2016
  • Computer Science
  • ArXiv
  • Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates. [...] Key Method We apply this to dependency parsing and tagging, where we use the hidden layer of the tagger network as a representation of the input tokens for the parser. At test time, our parser does not require predicted POS tags. On 19 languages from the Universal Dependencies, our method is 1.3% (absolute) more accurate than a state-of-the-art graph-based approach and 2.7…Expand Abstract
    Deep Multitask Learning for Semantic Dependency Parsing
    • 98
    • Open Access
    CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
    • 231
    • Open Access
    A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing
    • 30
    • Highly Influenced
    • Open Access
    A Primer on Neural Network Models for Natural Language Processing
    • 565
    • Open Access
    Semi-Supervised Sequence Modeling with Cross-View Training
    • 125
    • Open Access
    Combining Global Models for Parsing Universal Dependencies
    • 20
    • Open Access
    An improved neural network model for joint POS tagging and dependency parsing
    • 26
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Natural Language Processing (Almost) from Scratch
    • 5,434
    • Open Access
    Simple Semi-supervised Dependency Parsing
    • 486
    • Open Access
    Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs
    • 260
    • Highly Influential
    • Open Access
    A Universal Part-of-Speech Tagset
    • 781
    • Open Access
    Generating Typed Dependency Parses from Phrase Structure Parses
    • 2,424
    • Highly Influential
    • Open Access
    Joint Models for Chinese POS Tagging and Dependency Parsing
    • 71
    • Open Access