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/Multitask DPR + BART

Multitask DPR + BART

Reported on 56 benchmarks across 6 tasks

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

Natural Language Processing56 results

  • Question AnsweringonKILT: TriviaQA
    EM
    59.6
    best: 76.27 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    F1
    66.53
    best: 81.4 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    KILT-EM
    42.36
    best: 57.91 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    KILT-F1
    46.19
    best: 61.78 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    R-Prec
    61.49
    best: 72.68 (Re2G)
  • Question AnsweringonKILT: TriviaQA
    Recall@5
    68.33
    best: 76.36 (intersect)
  • Question AnsweringonKILT: Natural Questions
    EM
    39.75
    best: 53.74 (intersect)
  • Question AnsweringonKILT: Natural Questions
    F1
    48.43
    best: 62.24 (intersect)
  • Question AnsweringonKILT: Natural Questions
    KILT-EM
    29.09
    best: 43.56 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    KILT-F1
    34.7
    best: 49.8 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    R-Prec
    59.42
    best: 70.78 (Re2G)
  • Question AnsweringonKILT: Natural Questions
    Recall@5
    68.24
    best: 76.63 (Re2G)
  • Question AnsweringonKILT: HotpotQA
    EM
    31.77
    best: 40.46 (intersect)
  • Question AnsweringonKILT: HotpotQA
    F1
    41.56
    best: 51.44 (intersect)
  • Question AnsweringonKILT: HotpotQA
    KILT-EM
    9.53
    best: 18.06 (intersect)
  • Question AnsweringonKILT: HotpotQA
    KILT-F1
    11.27
    best: 21.42 (intersect)
  • Question AnsweringonKILT: HotpotQA
    R-Prec
    42.92
    best: 58.83 (intersect)
  • Question AnsweringonKILT: HotpotQA
    Recall@5
    28.39
    best: 51.03 (intersect)
  • Entity LinkingonKILT: AIDA-YAGO2
    Accuracy
    82.61
    best: 89.85 (GENRE)
  • Entity LinkingonKILT: AIDA-YAGO2
    KILT-AC
    24.67
    best: 89.85 (GENRE)
  • Entity LinkingonKILT: AIDA-YAGO2
    R-Prec
    26.48
    best: 89.98 (chriskuei)
  • Entity LinkingonKILT: AIDA-YAGO2
    Recall@5
    39.46
    best: 94.85 (chriskuei)
  • Slot FillingonKILT: Zero Shot RE
    Accuracy
    57.95
    best: 74.63 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    F1
    63.75
    best: 79.66 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    KILT-AC
    50.64
    best: 73.2 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    KILT-F1
    55.44
    best: 78.12 (single ngram)
  • Slot FillingonKILT: Zero Shot RE
    R-Prec
    80.91
    best: 98.49 (KGI_1)
  • Slot FillingonKILT: Zero Shot RE
    Recall@5
    93.05
    best: 99.34 (single ngram)
  • Fact VerificationonKILT: FEVER
    Accuracy
    86.32
    best: 89.55 (Re2G)
  • Fact VerificationonKILT: FEVER
    KILT-AC
    63.94
    best: 78.53 (Re2G)
  • Fact VerificationonKILT: FEVER
    R-Prec
    74.48
    best: 88.92 (Re2G)
  • Fact VerificationonKILT: FEVER
    Recall@5
    87.52
    best: 92.52 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    EM
    59.6
    best: 76.27 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    F1
    66.53
    best: 81.4 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    KILT-EM
    42.36
    best: 57.91 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    KILT-F1
    46.19
    best: 61.78 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    R-Prec
    61.49
    best: 72.68 (Re2G)
  • Open-Domain Question AnsweringonKILT: TriviaQA
    Recall@5
    68.33
    best: 76.36 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    EM
    39.75
    best: 53.74 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    F1
    48.43
    best: 62.24 (intersect)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    KILT-EM
    29.09
    best: 43.56 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    KILT-F1
    34.7
    best: 49.8 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    R-Prec
    59.42
    best: 70.78 (Re2G)
  • Open-Domain Question AnsweringonKILT: Natural Questions
    Recall@5
    68.24
    best: 76.63 (Re2G)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    EM
    31.77
    best: 40.46 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    F1
    41.56
    best: 51.44 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    KILT-EM
    9.53
    best: 18.06 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    KILT-F1
    11.27
    best: 21.42 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    R-Prec
    42.92
    best: 58.83 (intersect)
  • Open-Domain Question AnsweringonKILT: HotpotQA
    Recall@5
    28.39
    best: 51.03 (intersect)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    F1
    15.12
    best: 19.19 (Hindsight)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    KILT-F1
    6.96
    best: 13.39 (Hindsight)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    KILT-RL
    5.91
    best: 11.92 (Hindsight)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    R-Prec
    41.06
    best: 64.79 (chriskuei)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    ROUGE-L
    13.27
    best: 17.06 (Hindsight)
  • Open-Domain DialogonKILT: Wizard of Wikipedia
    Recall@5
    67.13
    best: 82.15 (chriskuei)