Corpus ID: 3608234

Generating Wikipedia by Summarizing Long Sequences

@article{Liu2018GeneratingWB,
  title={Generating Wikipedia by Summarizing Long Sequences},
  author={Peter J. Liu and Mohammad Saleh and Etienne Pot and Ben Goodrich and Ryan Sepassi and Lukasz Kaiser and Noam Shazeer},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.10198}
}
  • Peter J. Liu, Mohammad Saleh, +4 authors Noam Shazeer
  • Published in ICLR 2018
  • Computer Science
  • ArXiv
  • We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents. [...] Key Method For the abstractive model, we introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. We show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, we show it can extract…Expand Abstract

    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 151 CITATIONS

    About ? Extreme Summarization with Topic-Aware Convolutional Neural Networks

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Hierarchical Transformers for Multi-Document Summarization

    VIEW 15 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Automatic text summarization

    VIEW 1 EXCERPT
    CITES METHODS

    Unsupervised Neural Multi-document Abstractive Summarization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Hierarchical Text Generation using an Outline

    VIEW 1 EXCERPT
    CITES METHODS

    Joint Parsing and Generation for Abstractive Summarization

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 21 Highly Influenced Citations

    • Averaged 69 Citations per year from 2018 through 2019

    • 151% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 16 REFERENCES