Substance over Style: Document-Level Targeted Content Transfer

@inproceedings{Hegel2020SubstanceOS,
  title={Substance over Style: Document-Level Targeted Content Transfer},
  author={Allison Hegel and Sudha Rao and A. Çelikyilmaz and B. Dolan},
  booktitle={EMNLP},
  year={2020}
}
  • Allison Hegel, Sudha Rao, +1 author B. Dolan
  • Published in EMNLP 2020
  • Computer Science
  • Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an existing document to fit a set of constraints. Although sentence-level rewriting has been fairly well-studied, little work has addressed the challenge of rewriting an entire document coherently. In this work, we introduce the task of document-level targeted content transfer and address it in the recipe domain, with a recipe as the document and a dietary restriction (such as vegan or dairy… CONTINUE READING

    References

    SHOWING 1-10 OF 35 REFERENCES
    Adapting Language Models for Non-Parallel Author-Stylized Rewriting
    • 12
    • PDF
    Plug and Play Language Models: A Simple Approach to Controlled Text Generation
    • 90
    • Highly Influential
    • PDF
    Language Models are Unsupervised Multitask Learners
    • 2,297
    • PDF
    CTRL: A Conditional Transformer Language Model for Controllable Generation
    • 194
    • Highly Influential
    • PDF
    Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models
    • 84
    • PDF
    Using Whole Document Context in Neural Machine Translation
    • 9
    • PDF
    A Survey on Document-level Machine Translation: Methods and Evaluation
    • 8
    Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
    • 221
    • PDF
    Toward Controlled Generation of Text
    • 521
    • PDF
    Building Language Models for Text with Named Entities
    • 18
    • PDF