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/BERT + DPR

BERT + DPR

Reported on 46 benchmarks across 4 tasks

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

Natural Language Processing46 results

  • Question AnsweringonKILT: TriviaQA
    EM
    70.38
    best: 76.27 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    F1
    74.41
    best: 81.4 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    KILT-EM
    34.48
    best: 57.91 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    KILT-F1
    36.28
    best: 61.78 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    R-Prec
    43.4
    best: 72.68 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    Recall@5
    31.45
    best: 76.36 (intersect)
  • Question AnsweringonKILT: Natural Questions
    EM
    38.64
    best: 53.74 (intersect)
  • Question AnsweringonKILT: Natural Questions
    F1
    47.09
    best: 62.24 (intersect)
  • Question AnsweringonKILT: Natural Questions
    KILT-EM
    31.99
    best: 43.56 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    KILT-F1
    37.58
    best: 49.8 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    R-Prec
    60.66
    best: 70.78 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    Recall@5
    46.79
    best: 76.63 (Re2G)
  • Question AnsweringonKILT: HotpotQA
    EM
    11.29
    best: 40.46 (intersect)
  • Question AnsweringonKILT: HotpotQA
    F1
    17.35
    best: 51.44 (intersect)
  • Question AnsweringonKILT: HotpotQA
    KILT-EM
    0.74
    best: 18.06 (intersect)
  • Question AnsweringonKILT: HotpotQA
    KILT-F1
    1.26
    best: 21.42 (intersect)
  • Question AnsweringonKILT: HotpotQA
    R-Prec
    25.04
    best: 58.83 (intersect)
  • Question AnsweringonKILT: HotpotQA
    Recall@5
    10.4
    best: 51.03 (intersect)
  • Slot FillingonKILT: Zero Shot RE
    Accuracy
    6.93
    best: 74.63 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    F1
    37.28
    best: 79.66 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    KILT-AC
    4.47
    best: 73.2 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    KILT-F1
    27.09
    best: 78.12 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    R-Prec
    40.11
    best: 98.49 (KGI_1)
  • Slot FillingonKILT: Zero Shot RE
    Recall@5
    40.11
    best: 99.34 (single ngram)
  • Fact VerificationonKILT: FEVER
    Accuracy
    69.68
    best: 89.55 (Re2G)
  • Fact VerificationonKILT: FEVER
    KILT-AC
    58.58
    best: 78.53 (Re2G)
  • Fact VerificationonKILT: FEVER
    R-Prec
    72.93
    best: 88.92 (Re2G)
  • Fact VerificationonKILT: FEVER
    Recall@5
    73.52
    best: 92.52 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    EM
    70.38
    best: 76.27 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    F1
    74.41
    best: 81.4 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    KILT-EM
    34.48
    best: 57.91 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    KILT-F1
    36.28
    best: 61.78 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    R-Prec
    43.4
    best: 72.68 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    Recall@5
    31.45
    best: 76.36 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    EM
    38.64
    best: 53.74 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    F1
    47.09
    best: 62.24 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    KILT-EM
    31.99
    best: 43.56 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    KILT-F1
    37.58
    best: 49.8 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    R-Prec
    60.66
    best: 70.78 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    Recall@5
    46.79
    best: 76.63 (Re2G)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    EM
    11.29
    best: 40.46 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    F1
    17.35
    best: 51.44 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    KILT-EM
    0.74
    best: 18.06 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    KILT-F1
    1.26
    best: 21.42 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    R-Prec
    25.04
    best: 58.83 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    Recall@5
    10.4
    best: 51.03 (intersect)