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/JointGT Baseline

JointGT Baseline

Reported on 28 benchmarks across 4 tasks

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

Adversarial17 results

  • Text GenerationonDART
    BLEU
    47.51
    best: 48.74 (T5B Baseline)
  • Text GenerationonDART
    FactSpotter
    0.9586
    best: 97.6 (FactT5B)
  • Text GenerationonDART
    METEOR
    0.4043
    best: 40.74 (T5B Baseline)
  • Text GenerationonWebNLG
    BLEU
    67.08
    best: 67.32 (Control Prefixes (A1, T5-large))
  • Text GenerationonWebNLG
    FactSpotter
    99.09
    best: 99.71 (FactT5B)
  • Text GenerationonWebNLG
    METEOR
    48.34
    best: 48.35 (T5B Baseline)
  • Text GenerationonDART
    BLEU
    47.51
    best: 48.74 (T5B Baseline)
  • Text GenerationonDART
    FactSpotter
    95.86
    best: 97.6 (FactT5B)
  • Text GenerationonDART
    METEOR
    40.43
    best: 40.74 (T5B Baseline)
  • Text GenerationonWebNLG 2.0 (Constrained)
    BLEU
    67.08
  • Text GenerationonWebNLG 2.0 (Constrained)
    FactSpotter
    99.44
    best: 99.71 (FactT5B)
  • Text GenerationonWebNLG 2.0 (Constrained)
    METEOR
    48.34
    best: 48.35 (T5B Baseline)
  • Text GenerationonDART
    BERT
    0.9492
    best: 0.9505 (T5B Baseline)
  • Text GenerationonDART
    BLEU
    47.51
    best: 48.74 (T5B Baseline)
  • Text GenerationonDART
    BLEURT
    0.6733
    best: 0.6749 (T5B Baseline)
  • Text GenerationonDART
    FactSpotter
    95.86
    best: 97.6 (FactT5B)
  • Text GenerationonDART
    METEOR
    0.4043
    best: 40.74 (T5B Baseline)

Natural Language Processing17 results

  • Data-to-Text GenerationonWebNLG
    BLEU
    67.08
    best: 67.32 (Control Prefixes (A1, T5-large))
  • Data-to-Text GenerationonWebNLG
    FactSpotter
    99.09
    best: 99.71 (FactT5B)
  • Data-to-Text GenerationonWebNLG
    METEOR
    48.34
    best: 48.35 (T5B Baseline)
  • Data-to-Text GenerationonDART
    BLEU
    47.51
    best: 48.47 (T5B Baseline)
  • Data-to-Text GenerationonDART
    FactSpotter
    95.86
    best: 97.6 (FactT5B)
  • Data-to-Text GenerationonDART
    METEOR
    40.43
    best: 40.74 (T5B Baseline)
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    BLEU
    67.08
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    FactSpotter
    99.44
    best: 99.71 (FactT5B)
  • Data-to-Text GenerationonWebNLG 2.0 (Constrained)
    METEOR
    48.34
    best: 48.35 (T5B Baseline)
  • Table-to-Text GenerationonDART
    BERT
    0.9492
    best: 0.9505 (T5B Baseline)
  • Table-to-Text GenerationonDART
    BLEU
    47.51
    best: 48.47 (T5B Baseline)
  • Table-to-Text GenerationonDART
    BLEURT
    0.6733
    best: 0.6749 (T5B Baseline)
  • Table-to-Text GenerationonDART
    FactSpotter
    95.86
    best: 97.6 (FactT5B)
  • Table-to-Text GenerationonDART
    METEOR
    0.4043
    best: 0.4074 (T5B Baseline)
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    BLEU
    67.08
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    FactSpotter
    99.44
    best: 99.71 (FactT5B)
  • KG-to-Text GenerationonWebNLG 2.0 (Constrained)
    METEOR
    48.34
    best: 48.35 (T5B Baseline)