Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization

@article{Jha2020ArtemisAN,
  title={Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization},
  author={Rahul Jha and Keping Bi and Y. Li and M. Pakdaman and A. Çelikyilmaz and Ivan Zhiboedov and K. McDonald},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.02146}
}
  • Rahul Jha, Keping Bi, +4 authors K. McDonald
  • Published 2020
  • Computer Science
  • ArXiv
  • We describe Artemis (Annotation methodology for Rich, Tractable, Extractive, Multi-domain, Indicative Summarization), a novel hierarchical annotation process that produces indicative summaries for documents from multiple domains. Current summarization evaluation datasets are single-domain and focused on a few domains for which naturally occurring summaries can be easily found, such as news and scientific articles. These are not sufficient for training and evaluation of summarization models for… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper

    References

    SHOWING 1-10 OF 35 REFERENCES
    Using the Annotated Bibliography as a Resource for Indicative Summarization
    • 27
    • PDF
    Single-document and multi-document summary evaluation using Relative Utility
    • 25
    • Highly Influential
    • PDF
    HighRES: Highlight-based Reference-less Evaluation of Summarization
    • 15
    • PDF
    Generating Indicative-Informative Summaries with SumUM
    • 148
    • PDF
    BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
    • 28
    • PDF
    Looking for a Few Good Metrics: Automatic Summarization Evaluation - How Many Samples Are Enough?
    • 101
    • Highly Influential
    • PDF
    Automatically Assessing Machine Summary Content Without a Gold Standard
    • 124
    • PDF
    Applying Natural Language Generation to Indicative Summarization
    • 45
    • PDF
    Neural Summarization by Extracting Sentences and Words
    • 460
    • PDF