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/Charformer-Tall

Charformer-Tall

Reported on 8 benchmarks across 3 tasks · 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 Processing8 results

  • Semantic Textual SimilarityonQuora Question Pairs
    Accuracy· 2021-06-23
    91.4
    best: 92.4 (data2vec)
    SOTA
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Paraphrase IdentificationonQuora Question Pairs
    Accuracy· 2021-06-23
    91.4
    best: 92.4 (data2vec)
    SOTA
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Natural Language InferenceonMultiNLI
    Matched· 2021-06-23
    83.7
    best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Natural Language InferenceonMultiNLI
    Mismatched· 2021-06-23
    84.4
    best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Semantic Textual SimilarityonMRPC
    F1· 2021-06-23
    91.4
    best: 92.5 (T5-3B)
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Semantic Textual SimilarityonSTS Benchmark
    Pearson Correlation· 2021-06-23
    0.873
    best: 0.929 (MT-DNN-SMART)
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Semantic Textual SimilarityonQuora Question Pairs
    F1· 2021-06-23
    88.5
    best: 90.7 (ALICE)
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672
  • Paraphrase IdentificationonQuora Question Pairs
    F1· 2021-06-23
    88.5
    best: 90.7 (ALICE)
    Charformer: Fast Character Transformers via Gradient-based Subword TokenizationarXiv:2106.12672