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/SciFive-large

SciFive-large

Reported on 7 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Natural Language Processing4 results

  • Natural Language InferenceonMedNLI
    Accuracy· 2021-05-28
    86.57
    best: 86.59 (ClinicalMosaic)
    SOTA
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598
  • Natural Language InferenceonMedNLI
    Params (M)· 2021-05-28
    738
    SOTA
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598
  • Text ClassificationonHOC
    F1· 2021-05-28
    86.08
    best: 88.1 (BioLinkBERT (large))
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598
  • Document ClassificationonHOC
    F1· 2021-05-28
    86.08
    best: 88.1 (BioLinkBERT (large))
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598

Medical2 results

  • Information ExtractiononDDI extraction 2013 corpus
    F1· 2021-05-28
    0.8367
    best: 0.8408 (DESC+MOL+SciBERT)
    SOTA
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598
  • Information ExtractiononDDI extraction 2013 corpus
    Micro F1· 2021-05-28
    83.67
    best: 84.08 (DESC+MOL+SciBERT)
    SOTA
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598

Methodology1 result

  • ClassificationonHOC
    F1· 2021-05-28
    86.08
    best: 88.1 (BioLinkBERT (large))
    SciFive: a text-to-text transformer model for biomedical literaturearXiv:2106.03598