Neural Poetry Translation

  title={Neural Poetry Translation},
  author={Marjan Ghazvininejad and Yejin Choi and Kevin Knight},
  • Marjan Ghazvininejad, Yejin Choi, Kevin Knight
  • Published in NAACL-HLT 2018
  • Computer Science
  • We present the first neural poetry translation system. Unlike previous works that often fail to produce any translation for fixed rhyme and rhythm patterns, our system always translates a source text to an English poem. Human evaluation of the translations ranks the quality as acceptable 78.2% of the time. 
    9 Citations

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    The Challenges of Using Neural Machine Translation for Literature
    • 3
    Automatic Machine Translation of Poetry and a Low-Resource Language Pair
    Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation
    • Z. Liu, Z. Fu, +4 authors Jie Zhou
    • Computer Science
    • ACL
    • 2019
    • 7
    • PDF
    Learning Rhyming Constraints using Structured Adversaries
    • 2
    • PDF
    Syllabification of the Divine Comedy
    Neural Language Generation: Formulation, Methods, and Evaluation
    • 2
    • Highly Influenced
    • PDF
    A General-Purpose Algorithm for Constrained Sequential Inference
    • 1
    • PDF


    'Poetic' Statistical Machine Translation: Rhyme and Meter
    • 49
    • PDF
    Automatic Analysis of Rhythmic Poetry with Applications to Generation and Translation
    • 110
    • PDF
    Generating Topical Poetry
    • 86
    • PDF
    PoeTryMe : a versatile platform for poetry generation
    • 87
    • PDF
    Automatically Generating Rhythmic Verse with Neural Networks
    • 27
    • PDF
    Generating Chinese Classical Poems with Statistical Machine Translation Models
    • 85
    Generating Chinese Classical Poems with RNN Encoder-Decoder
    • 62
    • PDF
    Chinese Poetry Generation with Recurrent Neural Networks
    • 214
    • PDF
    A Survey on Intelligent Poetry Generation: Languages, Features, Techniques, Reutilisation and Evaluation
    • 32
    • PDF