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/GRN

GRN

Reported on 16 benchmarks across 4 tasks · 3 papers · 8 SOTA

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

Natural Language Processing16 results

  • Visual Question Answering (VQA)onGQA Test2019
    Accuracy· 2019-07-23
    61.22
    best: 89.3 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Binary· 2019-07-23
    78.69
    best: 91.2 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Consistency· 2019-07-23
    90.31
    best: 98.4 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Distribution· 2019-07-23
    6.77
    best: 93.08 (GlobalPrior)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Open· 2019-07-23
    45.81
    best: 87.4 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Plausibility· 2019-07-23
    85.43
    best: 97.2 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Visual Question Answering (VQA)onGQA Test2019
    Validity· 2019-07-23
    96.36
    best: 98.9 (human)
    SOTA
    Bilinear Graph Networks for Visual Question AnsweringarXiv:1907.09815
  • Graph-to-SequenceonLDC2015E86:
    BLEU· uses extra data· 2018-05-07
    33.6
    SOTA
    A Graph-to-Sequence Model for AMR-to-Text GenerationarXiv:1805.02473
  • Named Entity Recognition (NER)onOntonotes v5 (English)
    F1· 2019-07-12
    87.67
    best: 92.07 (BERT-MRC+DSC)
    GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity RecognitionarXiv:1907.05611
  • Named Entity Recognition (NER)onCoNLL 2003 (English)
    F1· 2019-07-12
    92.34
    best: 94.6 (ACE + document-context)
    GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity RecognitionarXiv:1907.05611
  • Question AnsweringonHotpotQA
    ANS-EM
    0.273
    best: 0.727 (Beam Retrieval)
  • Question AnsweringonHotpotQA
    ANS-F1
    0.365
    best: 0.85 (Beam Retrieval)
  • Question AnsweringonHotpotQA
    JOINT-EM
    0.074
    best: 0.505 (Beam Retrieval)
  • Question AnsweringonHotpotQA
    JOINT-F1
    0.236
    best: 0.775 (Beam Retrieval)
  • Question AnsweringonHotpotQA
    SUP-EM
    0.122
    best: 0.663 (Beam Retrieval)
  • Question AnsweringonHotpotQA
    SUP-F1
    0.488
    best: 0.901 (Beam Retrieval)