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/UMS_BERT+

UMS_BERT+

Reported on 12 benchmarks across 1 task · 1 paper · 8 SOTA

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

Natural Language Processing12 results

  • Conversational Response SelectiononDouban
    MAP· 2020-09-10
    0.625
    best: 0.651 (SEMSOL(W/o utterances))
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononDouban
    MRR· 2020-09-10
    0.664
    best: 0.688 (Uni-Enc+BERT-FP)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononDouban
    P@1· 2020-09-10
    0.499
    best: 0.518 (Uni-Enc+BERT-FP)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononDouban
    R10@1· 2020-09-10
    0.318
    best: 0.33 (SEMSOL)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononDouban
    R10@5· 2020-09-10
    0.858
    best: 0.877 (SEMSOL(W/o utterances))
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononE-commerce
    R10@1· 2020-09-10
    0.762
    best: 0.957 (BERT-FP+EDHNS)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononE-commerce
    R10@2· 2020-09-10
    0.905
    best: 0.986 (BERT-FP+EDHNS)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononE-commerce
    R10@5· 2020-09-10
    0.986
    best: 0.997 (BERT-FP+EDHNS)
    SOTA
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononDouban
    R10@2· 2020-09-10
    0.482
    best: 0.557 (Uni-Enc+BERT-FP)
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@1· 2020-09-10
    0.875
    best: 0.918 (Dial-MAE)
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@2· 2020-09-10
    0.942
    best: 0.965 (BERT-FP+EDHNS)
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@5· 2020-09-10
    0.988
    best: 0.994 (BERT-FP+EDHNS)
    Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response SelectionarXiv:2009.04703