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/SA-BERT

SA-BERT

Reported on 14 benchmarks across 1 task · 1 paper · 10 SOTA

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

Natural Language Processing14 results

  • Conversational Response SelectiononUbuntu IRC
    Accuracy· 2020-04-07
    60.42
    best: 63.64 (MPC-BERT)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    MAP· 2020-04-07
    0.619
    best: 0.651 (SEMSOL(W/o utterances))
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    MRR· 2020-04-07
    0.659
    best: 0.688 (Uni-Enc+BERT-FP)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    P@1· 2020-04-07
    0.496
    best: 0.518 (Uni-Enc+BERT-FP)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    R10@1· 2020-04-07
    0.313
    best: 0.33 (SEMSOL)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    R10@5· 2020-04-07
    0.847
    best: 0.877 (SEMSOL(W/o utterances))
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R2@1· 2020-04-07
    0.965
    best: 0.975 (BERT-SL)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononE-commerce
    R10@1· 2020-04-07
    0.704
    best: 0.957 (BERT-FP+EDHNS)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononE-commerce
    R10@2· 2020-04-07
    0.879
    best: 0.986 (BERT-FP+EDHNS)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononE-commerce
    R10@5· 2020-04-07
    0.985
    best: 0.997 (BERT-FP+EDHNS)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononDouban
    R10@2· 2020-04-07
    0.481
    best: 0.557 (Uni-Enc+BERT-FP)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@1· 2020-04-07
    0.855
    best: 0.918 (Dial-MAE)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@2· 2020-04-07
    0.928
    best: 0.965 (BERT-FP+EDHNS)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
    R10@5· 2020-04-07
    0.983
    best: 0.994 (BERT-FP+EDHNS)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588