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/SciBERT (Base Vocab)

SciBERT (Base Vocab)

Reported on 19 benchmarks across 8 tasks · 1 paper

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

Natural Language Processing11 results

  • Relation ExtractiononChemProt
    F1· uses extra data· 2019-03-26
    73.7
    best: 83.64 (SciBert (Finetune))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Relation ExtractiononSciERC
    F1· uses extra data· 2019-03-26
    74.42
    best: 74.64 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Dependency ParsingonGENIA - UAS
    F1· uses extra data· 2019-03-26
    92.32
    best: 92.84 (BiLSTM-CRF)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Dependency ParsingonGENIA - LAS
    F1· uses extra data· 2019-03-26
    91.26
    best: 91.92 (BiLSTM-CRF)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Named Entity Recognition (NER)onNCBI-disease
    F1· uses extra data· 2019-03-26
    86.88
    best: 89.71 (BioBERT)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Named Entity Recognition (NER)onSciERC
    F1· uses extra data· 2019-03-26
    65.24
    best: 72.4 (SciDeBERTa v2)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Named Entity Recognition (NER)onBC5CDR
    F1· uses extra data· 2019-03-26
    88.11
    best: 91.9 (BINDER)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Named Entity Recognition (NER)onJNLPBA
    F1· uses extra data· 2019-03-26
    75.77
    best: 82 (KeBioLM)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Text ClassificationonPaper Field
    F1· uses extra data· 2019-03-26
    64.02
    best: 65.71 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Text ClassificationonScienceCite
    F1· uses extra data· 2019-03-26
    84.43
    best: 84.99 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Text ClassificationonPubMed 20k RCT
    F1· uses extra data· 2019-03-26
    86.81
    best: 92.6 (Hierarchical Neural Networks)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676

Other3 results

  • Sentence ClassificationonPaper Field
    F1· uses extra data· 2019-03-26
    64.02
    best: 65.71 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Sentence ClassificationonScienceCite
    F1· uses extra data· 2019-03-26
    84.43
    best: 84.99 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Sentence ClassificationonPubMed 20k RCT
    F1· uses extra data· 2019-03-26
    86.81
    best: 92.6 (Hierarchical Neural Networks)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676

Methodology3 results

  • ClassificationonPaper Field
    F1· uses extra data· 2019-03-26
    64.02
    best: 65.71 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • ClassificationonScienceCite
    F1· uses extra data· 2019-03-26
    84.43
    best: 84.99 (SciBERT (SciVocab))
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • ClassificationonPubMed 20k RCT
    F1· uses extra data· 2019-03-26
    86.81
    best: 92.6 (Hierarchical Neural Networks)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676

Medical2 results

  • Information ExtractiononEBM-NLP
    F1· uses extra data· 2019-03-26
    70.82
    best: 76.01 (VarMAE)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676
  • Participant Intervention Comparison Outcome ExtractiononEBM-NLP
    F1· uses extra data· 2019-03-26
    70.82
    best: 76.01 (VarMAE)
    SciBERT: A Pretrained Language Model for Scientific TextarXiv:1903.10676