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/USR

USR

Reported on 10 benchmarks across 4 tasks · 2 papers · 4 SOTA

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

Natural Language Processing9 results

  • Open-Domain DialogonUSR-TopicalChat
    Pearson Correlation· 2020-05-01
    0.422
    best: 0.4974 (Lin-Reg (all))
    SOTA
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Open-Domain DialogonUSR-TopicalChat
    Spearman Correlation· 2020-05-01
    0.4192
    best: 0.5109 (MDD-Eval)
    SOTA
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Dialogue EvaluationonUSR-TopicalChat
    Pearson Correlation· 2020-05-01
    0.422
    best: 0.4974 (Lin-Reg (all))
    SOTA
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Dialogue EvaluationonUSR-TopicalChat
    Spearman Correlation· 2020-05-01
    0.4192
    best: 0.5109 (MDD-Eval)
    SOTA
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Natural Language TransductiononLRS2
    Word Error Rate (WER)· uses extra data· 2024-11-04
    15.4
    best: 14.6 (Auto-AVSR)
    Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual InputsarXiv:2411.02256
  • Open-Domain DialogonUSR-PersonaChat
    Pearson Correlation· 2020-05-01
    0.4115
    best: 0.6087 (USR - DR (x = c))
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Open-Domain DialogonUSR-PersonaChat
    Spearman Correlation· 2020-05-01
    0.4693
    best: 0.5382 (Lin-Reg (all))
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Dialogue EvaluationonUSR-PersonaChat
    Pearson Correlation· 2020-05-01
    0.4115
    best: 0.6087 (USR - DR (x = c))
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456
  • Dialogue EvaluationonUSR-PersonaChat
    Spearman Correlation· 2020-05-01
    0.4693
    best: 0.5382 (Lin-Reg (all))
    USR: An Unsupervised and Reference Free Evaluation Metric for Dialog GenerationarXiv:2005.00456

Computer Vision1 result

  • LipreadingonLRS2
    Word Error Rate (WER)· uses extra data· 2024-11-04
    15.4
    best: 14.6 (Auto-AVSR)
    Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual InputsarXiv:2411.02256