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/AGIF

AGIF

Reported on 7 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing7 results

  • Slot FillingonMixSNIPS
    Micro F1· 2020-04-21
    94.5
    best: 97.2 (BiSLU)
    SOTA
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Intent DetectiononMixSNIPS
    Accuracy· 2020-04-21
    96.5
    best: 98.4 (SSRAN)
    SOTA
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Intent DetectiononMixSNIPS
    f1 macro· 2020-04-21
    98.6
    SOTA
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Slot FillingonATIS
    F1· 2020-04-21
    0.96
    best: 0.9846 (CTRAN)
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Slot FillingonSNIPS
    F1· 2020-04-21
    94.8
    best: 98.3 (CTRAN)
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Intent DetectiononATIS
    Accuracy· 2020-04-21
    97.1
    best: 98.99 (Bi-model with decoder)
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087
  • Intent DetectiononSNIPS
    Accuracy· 2020-04-21
    98.1
    best: 99.42 (CTRAN)
    AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot FillingarXiv:2004.10087