TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/end2end w/ inconsistency loss

end2end w/ inconsistency loss

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Knowledge Base3 results

  • Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2018-05-16
    40.68
    best: 48.18 (Scrambled code + broken (alter))
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266
  • Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2018-05-16
    17.97
    best: 24.02 (Pegasus)
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266
  • Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2018-05-16
    37.13
    best: 45.35 (Scrambled code + broken (alter))
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266

Natural Language Processing3 results

  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2018-05-16
    40.68
    best: 48.18 (Scrambled code + broken (alter))
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266
  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2018-05-16
    17.97
    best: 24.02 (Pegasus)
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266
  • Abstractive Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2018-05-16
    37.13
    best: 45.35 (Scrambled code + broken (alter))
    A Unified Model for Extractive and Abstractive Summarization using Inconsistency LossarXiv:1805.06266