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/LUKE 483M

LUKE 483M

Reported on 8 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Natural Language Processing8 results

  • Relation ExtractiononTACRED
    F1· 2020-10-02
    72.7
    best: 86.6 (RAG4RE)
    SOTA
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Relation ClassificationonTACRED
    F1· 2020-10-02
    72.7
    best: 76.8 (DeepStruct multi-task w/ finetune)
    SOTA
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Question AnsweringonSQuAD1.1
    F1· 2020-10-02
    95.4
    best: 95.719 ({ANNA} (single model))
    SOTA
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Named Entity Recognition (NER)onCoNLL 2003 (English)
    F1· 2020-10-02
    94.3
    best: 94.6 (ACE + document-context)
    SOTA
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Question AnsweringonSQuAD1.1 dev
    F1· 2020-10-02
    95
    best: 95.77 (XLNet+DSC)
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Question AnsweringonSQuAD2.0
    F1· 2020-10-02
    90.2
    best: 93.214 (IE-Net (ensemble))
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Common Sense ReasoningonReCoRD
    EM· 2020-10-02
    90.6
    best: 95.9 (Turing NLR v5 XXL 5.4B (fine-tuned))
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057
  • Common Sense ReasoningonReCoRD
    F1· 2020-10-02
    91.2
    best: 96.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
    LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionarXiv:2010.01057