Learning to Write with Cooperative Discriminators

@article{Holtzman2018LearningTW,
  title={Learning to Write with Cooperative Discriminators},
  author={Ari Holtzman and Jan Buys and Maxwell Forbes and Antoine Bosselut and David Golub and Yejin Choi},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.06087}
}
  • Ari Holtzman, Jan Buys, +3 authors Yejin Choi
  • Published 2018
  • Computer Science
  • ArXiv
  • Recurrent Neural Networks (RNNs) are powerful autoregressive sequence models, but when used to generate natural language their output tends to be overly generic, repetitive, and self-contradictory. We postulate that the objective function optimized by RNN language models, which amounts to the overall perplexity of a text, is not expressive enough to capture the notion of communicative goals described by linguistic principles such as Grice's Maxims. We propose learning a mixture of multiple… CONTINUE READING

    Tables and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 48 CITATIONS

    Towards Coherent and Cohesive Long-form Text Generation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    A Cross-Domain Transferable Neural Coherence Model

    VIEW 1 EXCERPT
    CITES BACKGROUND

    The Curious Case of Neural Text Degeneration

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Neural Text Generation with Unlikelihood Training

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Learning Rhyming Constraints using Structured Adversaries

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Sparse Text Generation

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 2 Highly Influenced Citations

    • Averaged 16 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 53 REFERENCES

    The Neural Noisy Channel

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Challenges in Data-to-Document Generation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL