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/StructBERTRoBERTa ensemble

StructBERTRoBERTa ensemble

Reported on 8 benchmarks across 4 tasks · 1 paper · 7 SOTA

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

Natural Language Processing8 results

  • Semantic Textual SimilarityonSTS Benchmark
    Pearson Correlation· 2019-08-13
    0.928
    best: 0.929 (MT-DNN-SMART)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Semantic Textual SimilarityonSTS Benchmark
    Spearman Correlation· 2019-08-13
    0.924
    best: 0.931 (Mnet-Sim)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Semantic Textual SimilarityonQuora Question Pairs
    Accuracy· 2019-08-13
    90.7
    best: 92.4 (data2vec)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Semantic Textual SimilarityonQuora Question Pairs
    F1· 2019-08-13
    74.4
    best: 90.7 (ALICE)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Sentiment AnalysisonSST-2 Binary classification
    Accuracy· 2019-08-13
    97.1
    best: 97.5 (T5-11B)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Paraphrase IdentificationonQuora Question Pairs
    Accuracy· 2019-08-13
    90.7
    best: 92.4 (data2vec)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Paraphrase IdentificationonQuora Question Pairs
    F1· 2019-08-13
    74.4
    best: 90.7 (ALICE)
    SOTA
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577
  • Natural Language InferenceonWNLI
    Accuracy· 2019-08-13
    89.7
    best: 95.9 (Turing NLR v5 XXL 5.4B (fine-tuned))
    StructBERT: Incorporating Language Structures into Pre-training for Deep Language UnderstandingarXiv:1908.04577