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+BERT-FP

SA-BERT+BERT-FP

Reported on 8 benchmarks across 1 task · 1 paper · 6 SOTA

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

Natural Language Processing8 results

  • Conversational Response SelectiononRRS
    MAP· 2020-04-07
    0.701
    best: 0.702 (BERT-FP)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS
    MRR· 2020-04-07
    0.715
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS
    P@1· 2020-04-07
    0.555
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS
    R10@1· 2020-04-07
    0.497
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS
    R10@2· 2020-04-07
    0.685
    best: 0.708 (BERT-FP)
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS
    R10@5· 2020-04-07
    0.931
    SOTA
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS Ranking Test
    NDCG@3· 2020-04-07
    0.674
    best: 0.679 (Poly-encoder)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588
  • Conversational Response SelectiononRRS Ranking Test
    NDCG@5· 2020-04-07
    0.753
    best: 0.765 (Poly-encoder)
    Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based ChatbotsarXiv:2004.03588