pipeline_tag: 句子相似度 tags:

• 句子转换器
• 特征提取
• 句子相似度
• 转换器
• MTEB model-index:
• name: mmlw-e5-base results:
  • task: type: 聚类 dataset: type: PL-MTEB/8tags-clustering name: MTEB 8TagsClustering config: 默认 split: 测试 revision: 无 metrics:
    • type: v_measure value: 30.249113010261492
  • task: type: 分类 dataset: type: PL-MTEB/allegro-reviews name: MTEB AllegroReviews config: 默认 split: 测试 revision: 无 metrics:
    • type: 准确率 value: 36.3817097415507
    • type: f1 value: 32.77742158736663
  • task: type: 检索 dataset: type: arguana-pl name: MTEB ArguAna-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 32.646
    • type: map_at_10 value: 49.488
    • type: map_at_100 value: 50.190999999999995
    • type: map_at_1000 value: 50.194
    • type: map_at_3 value: 44.749
    • type: map_at_5 value: 47.571999999999996
    • type: mrr_at_1 value: 34.211000000000006
    • type: mrr_at_10 value: 50.112
    • type: mrr_at_100 value: 50.836000000000006
    • type: mrr_at_1000 value: 50.839
    • type: mrr_at_3 value: 45.614
    • type: mrr_at_5 value: 48.242000000000004
    • type: ndcg_at_1 value: 32.646
    • type: ndcg_at_10 value: 58.396
    • type: ndcg_at_100 value: 61.285000000000004
    • type: ndcg_at_1000 value: 61.358999999999995
    • type: ndcg_at_3 value: 48.759
    • type: ndcg_at_5 value: 53.807
    • type: precision_at_1 value: 32.646
    • type: precision_at_10 value: 8.663
    • type: precision_at_100 value: 0.9900000000000001
    • type: precision_at_1000 value: 0.1
    • type: precision_at_3 value: 20.128
    • type: precision_at_5 value: 14.509
    • type: recall_at_1 value: 32.646
    • type: recall_at_10 value: 86.629
    • type: recall_at_100 value: 99.004
    • type: recall_at_1000 value: 99.57300000000001
    • type: recall_at_3 value: 60.38400000000001
    • type: recall_at_5 value: 72.54599999999999
  • task: type: 分类 dataset: type: PL-MTEB/cbd name: MTEB CBD config: 默认 split: 测试 revision: 无 metrics:
    • type: 准确率 value: 65.53999999999999
    • type: ap value: 19.75395945379771
    • type: f1 value: 55.00481388401326
  • task: type: 配对分类 dataset: type: PL-MTEB/cdsce-pairclassification name: MTEB CDSC-E config: 默认 split: 测试 revision: 无 metrics:
    • type: cos_sim_accuracy value: 89.5
    • type: cos_sim_ap value: 77.26879308078568
    • type: cos_sim_f1 value: 65.13157894736842
    • type: cos_sim_precision value: 86.8421052631579
    • type: cos_sim_recall value: 52.10526315789473
    • type: dot_accuracy value: 88.0
    • type: dot_ap value: 69.17235659054914
    • type: dot_f1 value: 65.71428571428571
    • type: dot_precision value: 71.875
    • type: dot_recall value: 60.526315789473685
    • type: euclidean_accuracy value: 89.5
    • type: euclidean_ap value: 77.1905400565015
    • type: euclidean_f1 value: 64.91803278688525
    • type: euclidean_precision value: 86.08695652173914
    • type: euclidean_recall value: 52.10526315789473
    • type: manhattan_accuracy value: 89.5
    • type: manhattan_ap value: 77.19531778873724
    • type: manhattan_f1 value: 64.72491909385113
    • type: manhattan_precision value: 84.03361344537815
    • type: manhattan_recall value: 52.63157894736842
    • type: max_accuracy value: 89.5
    • type: max_ap value: 77.26879308078568
    • type: max_f1 value: 65.71428571428571
  • task: type: STS dataset: type: PL-MTEB/cdscr-sts name: MTEB CDSC-R config: 默认 split: 测试 revision: 无 metrics:
    • type: cos_sim_pearson value: 93.18498922236566
    • type: cos_sim_spearman value: 93.26224500108704
    • type: euclidean_pearson value: 92.25462061070286
    • type: euclidean_spearman value: 93.18623989769242
    • type: manhattan_pearson value: 92.16291103586255
    • type: manhattan_spearman value: 93.14403078934417
  • task: type: 检索 dataset: type: dbpedia-pl name: MTEB DBPedia-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 8.268
    • type: map_at_10 value: 17.391000000000002
    • type: map_at_100 value: 24.266
    • type: map_at_1000 value: 25.844
    • type: map_at_3 value: 12.636
    • type: map_at_5 value: 14.701
    • type: mrr_at_1 value: 62.74999999999999
    • type: mrr_at_10 value: 70.25200000000001
    • type: mrr_at_100 value: 70.601
    • type: mrr_at_1000 value: 70.613
    • type: mrr_at_3 value: 68.083
    • type: mrr_at_5 value: 69.37100000000001
    • type: ndcg_at_1 value: 51.87500000000001
    • type: ndcg_at_10 value: 37.185
    • type: ndcg_at_100 value: 41.949
    • type: ndcg_at_1000 value: 49.523
    • type: ndcg_at_3 value: 41.556
    • type: ndcg_at_5 value: 39.278
    • type: precision_at_1 value: 63.24999999999999
    • type: precision_at_10 value: 29.225
    • type: precision_at_100 value: 9.745
    • type: precision_at_1000 value: 2.046
    • type: precision_at_3 value: 43.833
    • type: precision_at_5 value: 37.9
    • type: recall_at_1 value: 8.268
    • type: recall_at_10 value: 22.542
    • type: recall_at_100 value: 48.154
    • type: recall_at_1000 value: 72.62100000000001
    • type: recall_at_3 value: 13.818
    • type: recall_at_5 value: 17.137
  • task: type: 检索 dataset: type: fiqa-pl name: MTEB FiQA-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 16.489
    • type: map_at_10 value: 26.916
    • type: map_at_100 value: 28.582
    • type: map_at_1000 value: 28.774
    • type: map_at_3 value: 23.048
    • type: map_at_5 value: 24.977
    • type: mrr_at_1 value: 33.642
    • type: mrr_at_10 value: 41.987
    • type: mrr_at_100 value: 42.882
    • type: mrr_at_1000 value: 42.93
    • type: mrr_at_3 value: 39.48
    • type: mrr_at_5 value: 40.923
    • type: ndcg_at_1 value: 33.488
    • type: ndcg_at_10 value: 34.528
    • type: ndcg_at_100 value: 41.085
    • type: ndcg_at_1000 value: 44.474000000000004
    • type: ndcg_at_3 value: 30.469
    • type: ndcg_at_5 value: 31.618000000000002
    • type: precision_at_1 value: 33.488
    • type: precision_at_10 value: 9.783999999999999
    • type: precision_at_100 value: 1.6389999999999998
    • type: precision_at_1000 value: 0.22699999999999998
    • type: precision_at_3 value: 20.525
    • type: precision_at_5 value: 15.093
    • type: recall_at_1 value: 16.489
    • type: recall_at_10 value: 42.370000000000005
    • type: recall_at_100 value: 67.183
    • type: recall_at_1000 value: 87.211
    • type: recall_at_3 value: 27.689999999999998
    • type: recall_at_5 value: 33.408
  • task: type: 检索 dataset: type: hotpotqa-pl name: MTEB HotpotQA-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 37.373
    • type: map_at_10 value: 57.509
    • type: map_at_100 value: 58.451
    • type: map_at_1000 value: 58.524
    • type: map_at_3 value: 54.064
    • type: map_at_5 value: 56.257999999999996
    • type: mrr_at_1 value: 74.895
    • type: mrr_at_10 value: 81.233
    • type: mrr_at_100 value: 81.461
    • type: mrr_at_1000 value: 81.47
    • type: mrr_at_3 value: 80.124
    • type: mrr_at_5 value: 80.862
    • type: ndcg_at_1 value: 74.747
    • type: ndcg_at_10 value: 66.249
    • type: ndcg_at_100 value: 69.513
    • type: ndcg_at_1000 value: 70.896
    • type: ndcg_at_3 value: 61.312
    • type: ndcg_at_5 value: 64.132
    • type: precision_at_1 value: 74.747
    • type: precision_at_10 value: 13.873
    • type: precision_at_100 value: 1.641
    • type: precision_at_1000 value: 0.182
    • type: precision_at_3 value: 38.987
    • type: precision_at_5 value: 25.621
    • type: recall_at_1 value: 37.373
    • type: recall_at_10 value: 69.365
    • type: recall_at_100 value: 82.039
    • type: recall_at_1000 value: 91.148
    • type: recall_at_3 value: 58.48100000000001
    • type: recall_at_5 value: 64.051
  • task: type: 检索 dataset: type: msmarco-pl name: MTEB MSMARCO-PL config: 默认 split: 验证 revision: 无 metrics:
    • type: map_at_1 value: 16.753999999999998
    • type: map_at_10 value: 26.764
    • type: map_at_100 value: 27.929
    • type: map_at_1000 value: 27.994999999999997
    • type: map_at_3 value: 23.527
    • type: map_at_5 value: 25.343
    • type: mrr_at_1 value: 17.192
    • type: mrr_at_10 value: 27.141
    • type: mrr_at_100 value: 28.269
    • type: mrr_at_1000 value: 28.327999999999996
    • type: mrr_at_3 value: 23.906
    • type: mrr_at_5 value: 25.759999999999998
    • type: ndcg_at_1 value: 17.177999999999997
    • type: ndcg_at_10 value: 32.539
    • type: ndcg_at_100 value: 38.383
    • type: ndcg_at_1000 value: 40.132
    • type: ndcg_at_3 value: 25.884
    • type: ndcg_at_5 value: 29.15
    • type: precision_at_1 value: 17.177999999999997
    • type: precision_at_10 value: 5.268
    • type: precision_at_100 value: 0.823
    • type: precision_at_1000 value: 0.097
    • type: precision_at_3 value: 11.122
    • type: precision_at_5 value: 8.338
    • type: recall_at_1 value: 16.753999999999998
    • type: recall_at_10 value: 50.388
    • type: recall_at_100 value: 77.86999999999999
    • type: recall_at_1000 value: 91.55
    • type: recall_at_3 value: 32.186
    • type: recall_at_5 value: 40.048
  • task: type: 分类 dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (pl) config: pl split: 测试 revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics:
    • type: 准确率 value: 70.9280430396772
    • type: f1 value: 68.7099581466286
  • task: type: 分类 dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (pl) config: pl split: 测试 revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics:
    • type: 准确率 value: 74.76126429051783
    • type: f1 value: 74.72274307018111
  • task: type: 检索 dataset: type: nfcorpus-pl name: MTEB NFCorpus-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 5.348
    • type: map_at_10 value: 12.277000000000001
    • type: map_at_100 value: 15.804000000000002
    • type: map_at_1000 value: 17.277
    • type: map_at_3 value: 8.783000000000001
    • type: map_at_5 value: 10.314
    • type: mrr_at_1 value: 43.963
    • type: mrr_at_10 value: 52.459999999999994
    • type: mrr_at_100 value: 53.233
    • type: mrr_at_1000 value: 53.26499999999999
    • type: mrr_at_3 value: 50.464
    • type: mrr_at_5 value: 51.548
    • type: ndcg_at_1 value: 40.711999999999996
    • type: ndcg_at_10 value: 33.709
    • type: ndcg_at_100 value: 31.398
    • type: ndcg_at_1000 value: 40.042
    • type: ndcg_at_3 value: 37.85
    • type: ndcg_at_5 value: 36.260999999999996
    • type: precision_at_1 value: 43.344
    • type: precision_at_10 value: 25.851000000000003
    • type: precision_at_100 value: 8.279
    • type: precision_at_1000 value: 2.085
    • type: precision_at_3 value: 36.326
    • type: precision_at_5 value: 32.074000000000005
    • type: recall_at_1 value: 5.348
    • type: recall_at_10 value: 16.441
    • type: recall_at_100 value: 32.975
    • type: recall_at_1000 value: 64.357
    • type: recall_at_3 value: 9.841999999999999
    • type: recall_at_5 value: 12.463000000000001
  • task: type: 检索 dataset: type: nq-pl name: MTEB NQ-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 24.674
    • type: map_at_10 value: 37.672
    • type: map_at_100 value: 38.767
    • type: map_at_1000 value: 38.82
    • type: map_at_3 value: 33.823
    • type: map_at_5 value: 36.063
    • type: mrr_at_1 value: 27.839000000000002
    • type: mrr_at_10 value: 40.129
    • type: mrr_at_100 value: 41.008
    • type: mrr_at_1000 value: 41.048
    • type: mrr_at_3 value: 36.718
    • type: mrr_at_5 value: 38.841
    • type: ndcg_at_1 value: 27.839000000000002
    • type: ndcg_at_10 value: 44.604
    • type: ndcg_at_100 value: 49.51
    • type: ndcg_at_1000 value: 50.841
    • type: ndcg_at_3 value: 37.223
    • type: ndcg_at_5 value: 41.073
    • type: precision_at_1 value: 27.839000000000002
    • type: precision_at_10 value: 7.5
    • type: precision_at_100 value: 1.03
    • type: precision_at_1000 value: 0.116
    • type: precision_at_3 value: 17.005
    • type: precision_at_5 value: 12.399000000000001
    • type: recall_at_1 value: 24.674
    • type: recall_at_10 value: 63.32299999999999
    • type: recall_at_100 value: 85.088
    • type: recall_at_1000 value: 95.143
    • type: recall_at_3 value: 44.157999999999994
    • type: recall_at_5 value: 53.054
  • task: type: 分类 dataset: type: laugustyniak/abusive-clauses-pl name: MTEB PAC config: 默认 split: 测试 revision: 无 metrics:
    • type: 准确率 value: 64.5033304373009
    • type: ap value: 75.81507275237081
    • type: f1 value: 62.24617820785985
  • task: type: 配对分类 dataset: type: PL-MTEB/ppc-pairclassification name: MTEB PPC config: 默认 split: 测试 revision: 无 metrics:
    • type: cos_sim_accuracy value: 85.39999999999999
    • type: cos_sim_ap value: 91.75881977787009
    • type: cos_sim_f1 value: 87.79264214046823
    • type: cos_sim_precision value: 88.68243243243244
    • type: cos_sim_recall value: 86.9205298013245
    • type: dot_accuracy value: 71.0
    • type: dot_ap value: 82.97829049033108
    • type: dot_f1 value: 78.77055039313797
    • type: dot_precision value: 69.30817610062893
    • type: dot_recall value: 91.22516556291392
    • type: euclidean_accuracy value: 85.2
    • type: euclidean_ap value: 91.85245521151309
    • type: euclidean_f1 value: 87.64607679465777
    • type: euclidean_precision value: 88.38383838383838
    • type: euclidean_recall value: 86.9205298013245
    • type: manhattan_accuracy value: 85.39999999999999
    • type: manhattan_ap value: 91.85497100160649
    • type: manhattan_f1 value: 87.77219430485762
    • type: manhattan_precision value: 88.8135593220339
    • type: manhattan_recall value: 86.75496688741721
    • type: max_accuracy value: 85.39999999999999
    • type: max_ap value: 91.85497100160649
    • type: max_f1 value: 87.79264214046823
  • task: type: 配对分类 dataset: type: PL-MTEB/psc-pairclassification name: MTEB PSC config: 默认 split: 测试 revision: 无 metrics:
    • type: cos_sim_accuracy value: 97.58812615955473
    • type: cos_sim_ap value: 99.14945370088302
    • type: cos_sim_f1 value: 96.06060606060606
    • type: cos_sim_precision value: 95.48192771084338
    • type: cos_sim_recall value: 96.64634146341463
    • type: dot_accuracy value: 95.17625231910947
    • type: dot_ap value: 97.05592933601112
    • type: dot_f1 value: 92.14501510574019
    • type: dot_precision value: 91.31736526946108
    • type: dot_recall value: 92.98780487804879
    • type: euclidean_accuracy value: 97.6808905380334
    • type: euclidean_ap value: 99.18538119402824
    • type: euclidean_f1 value: 96.20637329286798
    • type: euclidean_precision value: 95.77039274924472
    • type: euclidean_recall value: 96.64634146341463
    • type: manhattan_accuracy value: 97.58812615955473
    • type: manhattan_ap value: 99.17870990853292
    • type: manhattan_f1 value: 96.02446483180427
    • type: manhattan_precision value: 96.31901840490798
    • type: manhattan_recall value: 95.73170731707317
    • type: max_accuracy value: 97.6808905380334
    • type: max_ap value: 99.18538119402824
    • type: max_f1 value: 96.20637329286798
  • task: type: 分类 dataset: type: PL-MTEB/polemo2_in name: MTEB PolEmo2.0-IN config: 默认 split: 测试 revision: 无 metrics:
    • type: 准确率 value: 68.69806094182825
    • type: f1 value: 68.0619984307764
  • task: type: 分类 dataset: type: PL-MTEB/polemo2_out name: MTEB PolEmo2.0-OUT config: 默认 split: 测试 revision: 无 metrics:
    • type: 准确率 value: 35.80971659919028
    • type: f1 value: 31.13081621324864
  • task: type: 检索 dataset: type: quora-pl name: MTEB Quora-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 66.149
    • type: map_at_10 value: 80.133
    • type: map_at_100 value: 80.845
    • type: map_at_1000 value: 80.866
    • type: map_at_3 value: 76.983
    • type: map_at_5 value: 78.938
    • type: mrr_at_1 value: 76.09
    • type: mrr_at_10 value: 83.25099999999999
    • type: mrr_at_100 value: 83.422
    • type: mrr_at_1000 value: 83.42500000000001
    • type: mrr_at_3 value: 82.02199999999999
    • type: mrr_at_5 value: 82.831
    • type: ndcg_at_1 value: 76.14999999999999
    • type: ndcg_at_10 value: 84.438
    • type: ndcg_at_100 value: 86.048
    • type: ndcg_at_1000 value: 86.226
    • type: ndcg_at_3 value: 80.97999999999999
    • type: ndcg_at_5 value: 82.856
    • type: precision_at_1 value: 76.14999999999999
    • type: precision_at_10 value: 12.985
    • type: precision_at_100 value: 1.513
    • type: precision_at_1000 value: 0.156
    • type: precision_at_3 value: 35.563
    • type: precision_at_5 value: 23.586
    • type: recall_at_1 value: 66.149
    • type: recall_at_10 value: 93.195
    • type: recall_at_100 value: 98.924
    • type: recall_at_1000 value: 99.885
    • type: recall_at_3 value: 83.439
    • type: recall_at_5 value: 88.575
  • task: type: 检索 dataset: type: scidocs-pl name: MTEB SCIDOCS-PL config: 默认 split: 测试 revision: 无 metrics:
    • type: map_at_1 value: 3.688
    • type: map_at_10 value: 10.23
    • type: map_at_100 value: 12.077
    • type: map_at_1000 value: 12.382
    • type: map_at_3 value: 7.149
    • type: map_at_5 value: 8.689
    • type: mrr_at_1 value: 18.2
    • type: mrr_at_10 value: 28.816999999999997
    • type: mrr_at_100 value: 29.982
    • type: mrr_at_1000 value: 30.058
    • type: mrr_at_3 value: 25.983
    • type: mrr_at_5 value: 27.418
    • type: ndcg_at_1 value: 18.2
    • type: ndcg_at_10 value: 17.352999999999998
    • type: ndcg_at_100 value: 24.859
    • type: ndcg_at_1000 value: 30.535
    • type: ndcg_at_3 value: 16.17
    • type: ndcg_at_5 value: 14.235000000000001
    • type: precision_at_1 value: 18.2
    • type: precision_at_10 value: 9.19
    • type: precision_at_100 value: 2.01
    • type: precision_at_1000 value: 0.338
    • type: precision_at_3 value: 15.5
    • type: precision_at_5 value: 12.78
    • type: recall_at_1 value: 3.688
    • type: recall_at_10 value: 18.632
    • type: recall_at_100 value: 40.822
    • type: recall_at_1000 value: 68.552
    • type: recall_at_3 value: 9.423
    • type: recall_at_5 value: 12.943
  • task: type: 配对分类 dataset: type: PL-MTEB/sicke-pl-pairclassification name: MTEB SICK-E-PL config: 默认 split: 测试 revision: 无