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/BERT-ext + RL

BERT-ext + RL

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Natural Language Processing3 results

  • Extractive Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2019-09-19
    42.76
    best: 44.68 (HAHSum)
    SOTA
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752
  • Extractive Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2019-09-19
    39.11
    best: 40.75 (HAHSum)
    SOTA
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752
  • Extractive Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2019-09-19
    19.87
    best: 21.3 (HAHSum)
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752

Knowledge Base3 results

  • Text SummarizationonCNN / Daily Mail
    ROUGE-1· 2019-09-19
    42.76
    best: 48.18 (Scrambled code + broken (alter))
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752
  • Text SummarizationonCNN / Daily Mail
    ROUGE-2· 2019-09-19
    19.87
    best: 24.02 (Pegasus)
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752
  • Text SummarizationonCNN / Daily Mail
    ROUGE-L· 2019-09-19
    39.11
    best: 45.35 (Scrambled code + broken (alter))
    Summary Level Training of Sentence Rewriting for Abstractive SummarizationarXiv:1909.08752