Corpus ID: 1195002

A Dynamic Oracle for Arc-Eager Dependency Parsing

@inproceedings{Goldberg2012ADO,
  title={A Dynamic Oracle for Arc-Eager Dependency Parsing},
  author={Yoav Goldberg and Joakim Nivre},
  booktitle={COLING},
  year={2012}
}
  • Yoav Goldberg, Joakim Nivre
  • Published in COLING 2012
  • Computer Science
  • The standard training regime for transition-based dependency parsers makes use of an oracle, which predicts an optimal transition sequence for a sentence and its gold tree. [...] Key Method The oracle is efficient to implement and provably correct. We use the oracle to train a deterministic left-to-right dependency parser that is less sensitive to error propagation, using an online training procedure that also explores parser configurations resulting from non-optimal sequences of transitions. This new parser…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 161 CITATIONS

    Training Deterministic Parsers with Non-Deterministic Oracles

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Parsing Universal Dependency Treebanks using Neural Networks and Search-Based Oracle Milan

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    An Improved Non-monotonic Transition System for Dependency Parsing

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Transition-based Dependency DAG Parsing Using Dynamic Oracles

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Bidirectional Transition-Based Dependency Parsing

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2013
    2020

    CITATION STATISTICS

    • 9 Highly Influenced Citations

    • Averaged 24 Citations per year from 2018 through 2020