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-small 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: 31.772224277808153
  • 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: 33.03180914512922
    • type: f1 value: 29.800304217426167
  • 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: 28.804999999999996
    • type: map_at_10 value: 45.327
    • type: map_at_100 value: 46.17
    • type: map_at_1000 value: 46.177
    • type: map_at_3 value: 40.528999999999996
    • type: map_at_5 value: 43.335
    • type: mrr_at_1 value: 30.299
    • type: mrr_at_10 value: 45.763
    • type: mrr_at_100 value: 46.641
    • type: mrr_at_1000 value: 46.648
    • type: mrr_at_3 value: 41.074
    • type: mrr_at_5 value: 43.836999999999996
    • type: ndcg_at_1 value: 28.804999999999996
    • type: ndcg_at_10 value: 54.308
    • type: ndcg_at_100 value: 57.879000000000005
    • type: ndcg_at_1000 value: 58.048
    • type: ndcg_at_3 value: 44.502
    • type: ndcg_at_5 value: 49.519000000000005
    • type: precision_at_1 value: 28.804999999999996
    • type: precision_at_10 value: 8.286
    • type: precision_at_100 value: 0.984
    • type: precision_at_1000 value: 0.1
    • type: precision_at_3 value: 18.682000000000002
    • type: precision_at_5 value: 13.627
    • type: recall_at_1 value: 28.804999999999996
    • type: recall_at_10 value: 82.85900000000001
    • type: recall_at_100 value: 98.36399999999999
    • type: recall_at_1000 value: 99.644
    • type: recall_at_3 value: 56.04599999999999
    • type: recall_at_5 value: 68.137
  • 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: 64.24
    • type: ap value: 17.967103105024705
    • type: f1 value: 52.97375416129459
  • 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: 余弦相似度准确率 value: 88.8
    • type: 余弦相似度平均精度 value: 76.68028778789487
    • type: 余弦相似度f1 value: 66.82352941176471
    • type: 余弦相似度精确率 value: 60.42553191489362
    • type: 余弦相似度召回率 value: 74.73684210526315
    • type: 点积准确率 value: 88.1
    • type: 点积平均精度 value: 72.04910086070551
    • type: 点积f1 value: 66.66666666666667
    • type: 点积精确率 value: 69.31818181818183
    • type: 点积召回率 value: 64.21052631578948
    • type: 欧几里得准确率 value: 88.8
    • type: 欧几里得平均精度 value: 76.63591858340688
    • type: 欧几里得f1 value: 67.13286713286713
    • type: 欧几里得精确率 value: 60.25104602510461
    • type: 欧几里得召回率 value: 75.78947368421053
    • type: 曼哈顿准确率 value: 88.9
    • type: 曼哈顿平均精度 value: 76.54552849815124
    • type: 曼哈顿f1 value: 66.66666666666667
    • type: 曼哈顿精确率 value: 60.51502145922747
    • type: 曼哈顿召回率 value: 74.21052631578947
    • type: 最大准确率 value: 88.9
    • type: 最大平均精度 value: 76.68028778789487
    • type: 最大f1 value: 67.13286713286713
  • task: type: STS dataset: type: PL-MTEB/cdscr-sts name: MTEB CDSC-R config: 默认 split: 测试 revision: 无 metrics:
    • type: 余弦相似度皮尔逊 value: 91.64169404461497
    • type: 余弦相似度斯皮尔曼 value: 91.9755161377078
    • type: 欧几里得皮尔逊 value: 90.87481478491249
    • type: 欧几里得斯皮尔曼 value: 91.92362666383987
    • type: 曼哈顿皮尔逊 value: 90.8415510499638
    • type: 曼哈顿斯皮尔曼 value: 91.85927127194698
  • 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: 6.148
    • type: map_at_10 value: 12.870999999999999
    • type: map_at_100 value: 18.04
    • type: map_at_1000 value: 19.286
    • type: map_at_3 value: 9.156
    • type: map_at_5 value: 10.857999999999999
    • type: mrr_at_1 value: 53.25
    • type: mrr_at_10 value: 61.016999999999996
    • type: mrr_at_100 value: 61.48400000000001
    • type: mrr_at_1000 value: 61.507999999999996
    • type: mrr_at_3 value: 58.75
    • type: mrr_at_5 value: 60.375
    • type: ndcg_at_1 value: 41.0
    • type: ndcg_at_10 value: 30.281000000000002
    • type: ndcg_at_100 value: 33.955999999999996
    • type: ndcg_at_1000 value: 40.77
    • type: ndcg_at_3 value: 34.127
    • type: ndcg_at_5 value: 32.274
    • type: precision_at_1 value: 52.5
    • type: precision_at_10 value: 24.525
    • type: precision_at_100 value: 8.125
    • type: precision_at_1000 value: 1.728
    • type: precision_at_3 value: 37.083
    • type: precision_at_5 value: 32.15
    • type: recall_at_1 value: 6.148
    • type: recall_at_10 value: 17.866
    • type: recall_at_100 value: 39.213
    • type: recall_at_1000 value: 61.604000000000006
    • type: recall_at_3 value: 10.084
    • type: recall_at_5 value: 13.333999999999998
  • 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: 14.643
    • type: map_at_10 value: 23.166
    • type: map_at_100 value: 24.725
    • type: map_at_1000 value: 24.92
    • type: map_at_3 value: 20.166
    • type: map_at_5 value: 22.003
    • type: mrr_at_1 value: 29.630000000000003
    • type: mrr_at_10 value: 37.632
    • type: mrr_at_100 value: 38.512
    • type: mrr_at_1000 value: 38.578
    • type: mrr_at_3 value: 35.391
    • type: mrr_at_5 value: 36.857
    • type: ndcg_at_1 value: 29.166999999999998
    • type: ndcg_at_10 value: 29.749
    • type: ndcg_at_100 value: 35.983
    • type: ndcg_at_1000 value: 39.817
    • type: ndcg_at_3 value: 26.739
    • type: ndcg_at_5 value: 27.993000000000002
    • type: precision_at_1 value: 29.166999999999998
    • type: precision_at_10 value: 8.333
    • type: precision_at_100 value: 1.448
    • type: precision_at_1000 value: 0.213
    • type: precision_at_3 value: 17.747
    • type: precision_at_5 value: 13.58
    • type: recall_at_1 value: 14.643
    • type: recall_at_10 value: 35.247
    • type: recall_at_100 value: 59.150999999999996
    • type: recall_at_1000 value: 82.565
    • type: recall_at_3 value: 24.006
    • type: recall_at_5 value: 29.383
  • 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: 32.627
    • type: map_at_10 value: 48.041
    • type: map_at_100 value: 49.008
    • type: map_at_1000 value: 49.092999999999996
    • type: map_at_3 value: 44.774
    • type: map_at_5 value: 46.791
    • type: mrr_at_1 value: 65.28
    • type: mrr_at_10 value: 72.53500000000001
    • type: mrr_at_100 value: 72.892
    • type: mrr_at_1000 value: 72.909
    • type: mrr_at_3 value: 71.083
    • type: mrr_at_5 value: 71.985
    • type: ndcg_at_1 value: 65.253
    • type: ndcg_at_10 value: 57.13700000000001
    • type: ndcg_at_100 value: 60.783
    • type: ndcg_at_1000 value: 62.507000000000005
    • type: ndcg_at_3 value: 52.17
    • type: ndcg_at_5 value: 54.896
    • type: precision_at_1 value: 65.253
    • type: precision_at_10 value: 12.088000000000001
    • type: precision_at_100 value: 1.496
    • type: precision_at_1000 value: 0.172
    • type: precision_at_3 value: 32.96
    • type: precision_at_5 value: 21.931
    • type: recall_at_1 value: 32.627
    • type: recall_at_10 value: 60.439
    • type: recall_at_100 value: 74.80799999999999
    • type: recall_at_1000 value: 86.219
    • type: recall_at_3 value: 49.44
    • type: recall_at_5 value: 54.827999999999996
  • 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: 13.150999999999998
    • type: map_at_10 value: 21.179000000000002
    • type: map_at_100 value: 22.227
    • type: map_at_1000 value: 22.308
    • type: map_at_3 value: 18.473
    • type: map_at_5 value: 19.942999999999998
    • type: mrr_at_1 value: 13.467
    • type: mrr_at_10 value: 21.471
    • type: mrr_at_100 value: 22.509
    • type: mrr_at_1000 value: 22.585
    • type: mrr_at_3 value: 18.789
    • type: mrr_at_5 value: 20.262
    • type: ndcg_at_1 value: 13.539000000000001
    • type: ndcg_at_10 value: 25.942999999999998
    • type: ndcg_at_100 value: 31.386999999999997
    • type: ndcg_at_1000 value: 33.641
    • type: ndcg_at_3 value: 20.368
    • type: ndcg_at_5 value: 23.003999999999998
    • type: precision_at_1 value: 13.539000000000001
    • type: precision_at_10 value: 4.249
    • type: precision_at_100 value: 0.7040000000000001
    • type: precision_at_1000 value: 0.09
    • type: precision_at_3 value: 8.782
    • type: precision_at_5 value: 6.6049999999999995
    • type: recall_at_1 value: 13.150999999999998
    • type: recall_at_10 value: 40.698
    • type: recall_at_100 value: 66.71000000000001
    • type: recall_at_1000 value: 84.491
    • type: recall_at_3 value: 25.452
    • type: recall_at_5 value: 31.791000000000004
  • 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: 67.3537323470074
    • type: f1 value: 64.67852047603644
  • 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: 72.12508406186953
    • type: f1 value: 71.55887309568853
  • 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: 4.18
    • type: map_at_10 value: 9.524000000000001
    • type: map_at_100 value: 12.272
    • type: map_at_1000 value: 13.616
    • type: map_at_3 value: 6.717
    • type: map_at_5 value: 8.172
    • type: mrr_at_1 value: 37.152
    • type: mrr_at_10 value: 45.068000000000005
    • type: mrr_at_100 value: 46.026
    • type: mrr_at_1000 value: 46.085
    • type: mrr_at_3 value: 43.344
    • type: mrr_at_5 value: 44.412
    • type: ndcg_at_1 value: 34.52
    • type: ndcg_at_10 value: 27.604
    • type: ndcg_at_100 value: 26.012999999999998
    • type: ndcg_at_1000 value: 35.272
    • type: ndcg_at_3 value: 31.538
    • type: ndcg_at_5 value: 30.165999999999997
    • type: precision_at_1 value: 36.223
    • type: precision_at_10 value: 21.053
    • type: precision_at_100 value: 7.08
    • type: precision_at_1000 value: 1.9929999999999999
    • type: precision_at_3 value: 30.031000000000002
    • type: precision_at_5 value: 26.997
    • type: recall_at_1 value: 4.18
    • type: recall_at_10 value: 12.901000000000002
    • type: recall_at_100 value: 27.438000000000002
    • type: recall_at_1000 value: 60.768
    • type: recall_at_3 value: 7.492
    • type: recall_at_5 value: 10.05
  • 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: 17.965
    • type: map_at_10 value: 28.04
    • type: map_at_100 value: 29.217
    • type: map_at_1000 value: 29.285
    • type: map_at_3 value: 24.818
    • type: map_at_5 value: 26.617
    • type: mrr_at_1 value: 20.22
    • type: mrr_at_10 value: 30.148000000000003
    • type: mrr_at_100 value: 31.137999999999998
    • type: mrr_at_1000 value: 31.19
    • type: mrr_at_3 value: 27.201999999999998
    • type: mrr_at_5 value: 28.884999999999998
    • type: ndcg_at_1 value: 20.365
    • type: ndcg_at_10 value: 33.832
    • type: ndcg_at_100 value: 39.33
    • type: ndcg_at_1000 value: 41.099999999999994
    • type: ndcg_at_3 value: 27.46
    • type: ndcg_at_5 value: 30.584
    • type: precision_at_1 value: 20.365
    • type: precision_at_10 value: 5.849
    • type: precision_at_100 value: 0.8959999999999999
    • type: precision_at_1000 value: 0.107
    • type: precision_at_3 value: 12.64
    • type: precision_at_5 value: 9.334000000000001
    • type: recall_at_1 value: 17.965
    • type: recall_at_10 value: 49.503
    • type: recall_at_100 value: 74.351
    • type: recall_at_1000 value: 87.766
    • type: recall_at_3 value: 32.665
    • type: recall_at_5 value: 39.974
  • 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: 63.11323486823051
    • type: ap value: 74.53486257377787
    • type: f1 value: 60.631005373417736
  • 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: 余弦相似度准确率 value: 80.10000000000001
    • type: 余弦相似度平均精度 value: 89.69526236458292
    • type: 余弦相似度f1 value: 83.37468982630274
    • type: 余弦相似度精确率 value: 83.30578512396694
    • type: 余弦相似度召回率 value: 83.44370860927152
    • type: 点积准确率 value: 77.8
    • type: 点积平均精度 value: 87.72366051496104
    • type: 点积f1 value: 82.83752860411899
    • type: 点积精确率 value: 76.80339462517681
    • type: 点积召回率 value: 89.90066225165563
    • type: 欧几里得准确率 value: 80.10000000000001
    • type: 欧几里得平均精度 value: 89.61317191870039
    • type: 欧几里得f1 value: 83.40214698596202
    • type: 欧几里得精确率 value: 83.19604612850083
    • type: 欧几里得召回率 value: 83.6092715231788
    • type: 曼哈顿准确率 value: 79.60000000000001
    • type: 曼哈顿平均精度 value: 89.48363786968471
    • type: 曼哈顿f1 value: 82.96296296296296
    • type: 曼哈顿精确率 value: 82.48772504091653
    • type: 曼哈顿召回率 value: 83.44370860927152
    • type: 最大准确率 value: 80.10000000000001
    • type: 最大平均精度 value: 89.69526236458292
    • type: 最大f1 value: 83.40214698596202
  • 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: 余弦相似度准确率 value: 96.93877551020408
    • type: 余弦相似度平均精度 value: 98.86489482248999
    • type: 余弦相似度f1 value: 95.11111111111113
    • type: 余弦相似度精确率 value: 92.507204610951
    • type: 余弦相似度召回率 value: 97.86585365853658
    • type: 点积准确率 value: 95.73283858998145
    • type: 点积平均精度 value: 97.8261652492545
    • type: 点积f1 value: 93.21533923303835
    • type: 点积精确率 value: 90.28571428571428
    • type: 点积召回率 value: 96.34146341463415
    • type: 欧几里得准确率 value: 96.93877551020408
    • type: 欧几里得平均精度 value: 98.84837797066623
    • type: 欧几里得f1 value: 95.11111111111113
    • type: 欧几里得精确率 value: 92.507204610951
    • type: 欧几里得召回率 value: 97.86585365853658
    • type: 曼哈顿准确率 value: 96.84601113172542
    • type: 曼哈顿平均精度 value: 98.78659090944161
    • type: 曼哈顿f1 value: 94.9404761904762
    • type: 曼哈顿精确率 value: 92.73255813953489
    • type: 曼哈顿召回率 value: 97.2560975609756
    • type: 最大准确率 value: 96.93877551020408
    • type: 最大平均精度 value: 98.86489482248999
    • type: 最大f1 value: 95.11111111111113
  • 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: 63.961218836565095
    • type: f1 value: 64.3979989243291
  • 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: 40.32388663967612
    • type: f1 value: 32.339117999015755
  • 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: 62.757
    • type: map_at_10 value: 76.55999999999999
    • type: map_at_100 value: 77.328
    • type: map_at_1000 value: 77.35499999999999
    • type: map_at_3 value: 73.288
    • type: map_at_5 value: 75.25500000000001
    • type: mrr_at_1 value: 72.28
    • type: mrr_at_10 value: 79.879
    • type: mrr_at_100 value: 80.121
    • type: mrr_at_1000 value: 80.12700000000001
    • type: mrr_at_3 value: 78.40700000000001
    • type: mrr_at_5 value: 79.357
    • type: ndcg_at_1 value: 72.33000000000001
    • type: ndcg_at_10 value: 81.151
    • type: ndcg_at_100 value: 83.107
    • type: ndcg_at_1000 value: 83.397
    • type: ndcg_at_3 value: 77.3
    • type: ndcg_at_5 value: 79.307
    • type: precision_at_1 value: 72.33000000000001
    • type: precision_at_10 value: 12.587000000000002
    • type: precision_at_100 value: 1.488
    • type: precision_at_1000 value: 0.155
    • type: precision_at_3 value: 33.943
    • type: precision_at_5 value: 22.61
    • type: recall_at_1 value: 62.757
    • type: recall_at_10 value: 90.616
    • type: recall_at_100 value: 97.905
    • type: recall_at_1000 value: 99.618
    • type: recall_at_3 value: 79.928
    • type: recall_at_5 value: 85.30499999999999
  • 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: 3.313
    • type: map_at_10 value: 8.559999999999999
    • type: map_at_100 value: 10.177999999999999
    • type: map_at_1000 value: 10.459999999999999
    • type: map_at_3 value: 6.094
    • type: map_at_5 value: 7.323
    • type: mrr_at_1 value: 16.3
    • type: mrr_at_10 value: 25.579
    • type: mrr_at_100 value: 26.717000000000002
    • type: mrr_at_1000 value: 26.799
    • type: mrr_at_3 value: 22.583000000000002
    • type: mrr_at_5 value: 24.298000000000002
    • type: ndcg_at_1 value: 16.3
    • type: ndcg_at_10 value: 14.789
    • type: ndcg_at_100 value: 21.731
    • type: ndcg_at_1000 value: 27.261999999999997
    • type: ndcg_at_3 value: 13.74
    • type: ndcg_at_5 value: 12.199
    • type: precision_at_1 value: 16.3
    • type: precision_at_10 value: 7.779999999999999
    • type: precision_at_100 value: 1.79
    • type: precision_at_1000 value: 0