Left-to-Right Dependency Parsing with Pointer Networks

  title={Left-to-Right Dependency Parsing with Pointer Networks},
  author={Daniel Fern{\'a}ndez-Gonz{\'a}lez and Carlos G{\'o}mez-Rodr{\'i}guez},
  • Daniel Fernández-González, Carlos Gómez-Rodríguez
  • Published 2019
  • Computer Science
  • ArXiv
  • We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building $n$ attachments, with $n$ being the length of the input sentence. Similarly to the recent stack-pointer parser by Ma et al. (2018), we use the pointer network framework that, given a word, can directly point to a position from the sentence. However, our left-to-right approach is simpler than the original top-down stack-pointer parser (not requiring a stack) and reduces transition… CONTINUE READING
    25 Citations
    Multitask Pointer Network for Multi-Representational Parsing
    • 1
    • PDF
    Parsing as Tagging
    • 2
    • Highly Influenced
    • PDF
    Discontinuous Constituent Parsing with Pointer Networks
    • 6
    • PDF
    Parsing All: Syntax and Semantics, Dependencies and Spans
    • 9
    • PDF


    Stack-Pointer Networks for Dependency Parsing
    • 92
    • Highly Influential
    • PDF
    Dependency Parsing as Head Selection
    • 69
    • PDF
    Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task
    • 162
    • PDF
    Neural Probabilistic Model for Non-projective MST Parsing
    • 30
    • PDF
    Graph-based Dependency Parsing with Bidirectional LSTM
    • 110
    • PDF
    Analyzing and Integrating Dependency Parsers
    • 104
    • PDF