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/RoBERTa-base

RoBERTa-base

Reported on 8 benchmarks across 4 tasks · 2 papers · 2 SOTA

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

Natural Language Processing5 results

  • Entity ResolutiononWDC Products-50%cc-unseen-medium
    F1 (%)· 2023-01-23
    71.14
    SOTA
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521
  • Entity ResolutiononWDC Products-80%cc-seen-medium-multi
    F1 Micro· 2023-01-23
    52.03
    best: 88.63 (RoBERTa-SupCon)
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521
  • Entity ResolutiononWDC Products-80%cc-seen-medium
    F1 (%)· 2023-01-23
    72.18
    best: 89.61 (gpt4-0613_zeroshot)
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521
  • Reading ComprehensiononReClor
    Test· 2020-02-11
    48.5
    best: 80.6 (Rational Reasoner / IDOL)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Sentence CompletiononHONEST
    HONEST
    2.38
    best: 3.33 (BERT-large)

Knowledge Base3 results

  • Data IntegrationonWDC Products-50%cc-unseen-medium
    F1 (%)· 2023-01-23
    71.14
    SOTA
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521
  • Data IntegrationonWDC Products-80%cc-seen-medium-multi
    F1 Micro· 2023-01-23
    52.03
    best: 88.63 (RoBERTa-SupCon)
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521
  • Data IntegrationonWDC Products-80%cc-seen-medium
    F1 (%)· 2023-01-23
    72.18
    best: 89.61 (gpt4-0613_zeroshot)
    WDC Products: A Multi-Dimensional Entity Matching BenchmarkarXiv:2301.09521