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/Mirror-RoBERTa-base (unsup.)

Mirror-RoBERTa-base (unsup.)

Reported on 7 benchmarks across 1 task · 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 Processing7 results

  • Semantic Textual SimilarityonSTS13
    Spearman Correlation· 2021-04-16
    0.819
    best: 0.9058 (AnglE-LLaMA-7B)
    SOTA
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSTS16
    Spearman Correlation· 2021-04-16
    0.78
    best: 0.87 (AnglE-LLaMA-7B-v2)
    SOTA
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSTS14
    Spearman Correlation· 2021-04-16
    0.732
    best: 0.8689 (AnglE-LLaMA-13B)
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSTS15
    Spearman Correlation· 2021-04-16
    0.798
    best: 0.9004 (PromptEOL+CSE+LLaMA-30B)
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSICK
    Spearman Correlation· 2021-04-16
    0.706
    best: 0.8243 (PromCSE-RoBERTa-large (0.355B))
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSTS Benchmark
    Spearman Correlation· 2021-04-16
    0.787
    best: 0.931 (Mnet-Sim)
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027
  • Semantic Textual SimilarityonSTS12
    Spearman Correlation· 2021-04-16
    0.648
    best: 0.802 (PromptEOL+CSE+OPT-13B)
    Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersarXiv:2104.08027