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/LeakGAN

LeakGAN

Reported on 9 benchmarks across 1 task · 1 paper · 8 SOTA

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

Adversarial9 results

  • Text GenerationonCOCO Captions
    BLEU-2· 2017-09-24
    0.95
    best: 2 (tecpic)
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonCOCO Captions
    BLEU-3· 2017-09-24
    0.88
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonCOCO Captions
    BLEU-4· 2017-09-24
    0.778
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonCOCO Captions
    BLEU-5· 2017-09-24
    0.686
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonEMNLP2017 WMT
    BLEU-2· 2017-09-24
    0.956
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonEMNLP2017 WMT
    BLEU-3· 2017-09-24
    0.819
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonEMNLP2017 WMT
    BLEU-4· 2017-09-24
    0.627
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonEMNLP2017 WMT
    BLEU-5· 2017-09-24
    0.498
    SOTA
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624
  • Text GenerationonChinese Poems
    BLEU-2· 2017-09-24
    0.456
    best: 0.812 (RankGAN)
    Long Text Generation via Adversarial Training with Leaked InformationarXiv:1709.08624