Go Back

Correlation Results

Current Conditions

  • Human Assessment Type: Adequacy, 4-point scale
  • Target Language: English
  • Correlation Level: segment

Subdivisions

By track:

Ranking

Single Reference Track
RankMetric NameSpearman's RhoKendall's TauPearson's RGraphs
Value95% confidence intervalValue95% confidence intervalValue95% confidence interval
1SEPIA20.5439(0.4996, 0.5853)0.3982(0.3458, 0.4481)0.5008(0.4538, 0.5449)graph_scatterplot
2CDer-0.6041(-0.6413, -0.5641)-0.4419(-0.4896, -0.3917)-0.5772(-0.6163, -0.5352)graph_scatterplot
3ULCh0.5690(0.5264, 0.6087)0.4134(0.3617, 0.4625)0.5475(0.5035, 0.5887)graph_scatterplot
4TER-v0.7.25-0.5637(-0.6038, -0.5208)-0.4085(-0.4579, -0.3565)-0.5059(-0.5498, -0.4593)graph_scatterplot
5DP-Orp0.2646(0.2071, 0.3202)0.1857(0.1264, 0.2437)0.2896(0.2330, 0.3443)graph_scatterplot
6NIST-v11b0.5554(0.5119, 0.5961)0.4059(0.3539, 0.4555)0.5526(0.5089, 0.5934)graph_scatterplot
7ATEC40.5136(0.4675, 0.5570)0.3750(0.3216, 0.4261)0.5179(0.4720, 0.5610)graph_scatterplot
8ATEC10.5217(0.4760, 0.5646)0.3821(0.3290, 0.4328)0.5180(0.4721, 0.5611)graph_scatterplot
9mBLEU0.2462(0.1882, 0.3024)0.1692(0.1096, 0.2276)0.1871(0.1277, 0.2450)graph_scatterplot
10SNR0.5309(0.4858, 0.5731)0.3864(0.3334, 0.4369)0.5198(0.4740, 0.5627)graph_scatterplot
114-GRR0.5531(0.5095, 0.5939)0.3983(0.3460, 0.4483)0.4958(0.4485, 0.5403)graph_scatterplot
12ATEC20.5304(0.4853, 0.5727)0.3875(0.3346, 0.4380)0.5300(0.4848, 0.5723)graph_scatterplot
13SEPIA10.5413(0.4969, 0.5829)0.3970(0.3446, 0.4470)0.4982(0.4511, 0.5426)graph_scatterplot
14ULCopt0.6290(0.5908, 0.6644)0.4635(0.4144, 0.5099)0.6098(0.5701, 0.6466)graph_scatterplot
15mTER-0.1160(-0.1755, -0.0556)-0.0875(-0.1475, -0.0269)-0.1537(-0.2125, -0.0938)graph_scatterplot
16EDPM0.6110(0.5714, 0.6477)0.4427(0.3925, 0.4903)0.5917(0.5508, 0.6298)graph_scatterplot
17BLEU-40.5457(0.5016, 0.5870)0.3864(0.3334, 0.4369)0.4801(0.4319, 0.5255)graph_scatterplot
18METEOR-v0.60.6163(0.5771, 0.6526)0.4510(0.4012, 0.4981)0.6201(0.5812, 0.6561)graph_scatterplot
19RTE-MT0.5848(0.5434, 0.6234)0.4195(0.3681, 0.4683)0.5772(0.5352, 0.6163)graph_scatterplot
20BadgerLite0.4143(0.3627, 0.4634)0.2938(0.2372, 0.3483)0.3903(0.3376, 0.4407)graph_scatterplot
21METEOR-ranking0.5936(0.5528, 0.6316)0.4362(0.3856, 0.4841)0.5812(0.5395, 0.6201)graph_scatterplot
22LET0.5093(0.4629, 0.5530)0.3758(0.3224, 0.4268)0.5145(0.4684, 0.5579)graph_scatterplot
23DP-Or0.4804(0.4322, 0.5258)0.3569(0.3027, 0.4088)0.4800(0.4318, 0.5254)graph_scatterplot
24ATEC30.5300(0.4849, 0.5723)0.3873(0.3345, 0.4378)0.5304(0.4853, 0.5727)graph_scatterplot
25BLEU-v120.3342(0.2791, 0.3871)0.2670(0.2096, 0.3225)0.3577(0.3036, 0.4096)graph_scatterplot
26BEwT-E0.2974(0.2410, 0.3518)0.2312(0.1729, 0.2879)0.3478(0.2932, 0.4001)graph_scatterplot
27RTE0.5876(0.5463, 0.6260)0.4203(0.3690, 0.4691)0.5770(0.5350, 0.6161)graph_scatterplot
28DR-Or0.4600(0.4107, 0.5066)0.3331(0.2779, 0.3860)0.4722(0.4236, 0.5181)graph_scatterplot
29BleuSP0.5707(0.5283, 0.6103)0.4145(0.3629, 0.4636)0.5432(0.4989, 0.5847)graph_scatterplot
30SVM-Rank0.5752(0.5330, 0.6144)0.4206(0.3693, 0.4694)0.5520(0.5083, 0.5929)graph_scatterplot
31BLEU-10.5731(0.5308, 0.6125)0.4190(0.3676, 0.4678)0.5801(0.5383, 0.6190)graph_scatterplot
32Bleu-sbp0.3262(0.2708, 0.3794)0.2603(0.2027, 0.3160)0.3503(0.2959, 0.4025)graph_scatterplot
33invWer-0.5672(-0.6071, -0.5246)-0.4120(-0.4612, -0.3602)-0.5058(-0.5497, -0.4591)graph_scatterplot
34BLEU-v11b0.3262(0.2708, 0.3794)0.2603(0.2027, 0.3160)0.3503(0.2959, 0.4025)graph_scatterplot
35SR-Or0.4743(0.4258, 0.5200)0.3388(0.2838, 0.3915)0.4340(0.3834, 0.4821)graph_scatterplot
36Badger0.3357(0.2807, 0.3885)0.2368(0.1786, 0.2933)0.3373(0.2823, 0.3901)graph_scatterplot
37Meteor-v0.70.6009(0.5607, 0.6384)0.4422(0.3919, 0.4898)0.6078(0.5681, 0.6448)graph_scatterplot
38MaxSim0.5246(0.4791, 0.5673)0.3814(0.3283, 0.4322)0.5394(0.4949, 0.5811)graph_scatterplot
39TERp-0.6355(-0.6704, -0.5978)-0.4768(-0.5224, -0.4285)-0.6224(-0.6583, -0.5837)graph_scatterplot

39 metrics (including 7 baseline metrics)
1041 data points (total number of segments used)

Multiple References Track
RankMetric NameSpearman's RhoKendall's TauPearson's RGraphs
Value95% confidence intervalValue95% confidence intervalValue95% confidence interval
1SEPIA20.6292(0.5910, 0.6645)0.4625(0.4134, 0.5090)0.5733(0.5310, 0.6127)graph_scatterplot
2CDer-0.7128(-0.7414, -0.6815)-0.5298(-0.5721, -0.4846)-0.6950(-0.7251, -0.6622)graph_scatterplot
3ULCh0.6237(0.5851, 0.6594)0.4543(0.4048, 0.5013)0.6015(0.5612, 0.6389)graph_scatterplot
4TER-v0.7.25-0.6495(-0.6833, -0.6129)-0.4738(-0.5196, -0.4252)-0.5938(-0.6318, -0.5530)graph_scatterplot
5DP-Orp0.3844(0.3314, 0.4350)0.2737(0.2166, 0.3290)0.3833(0.3302, 0.4340)graph_scatterplot
6NIST-v11b0.6300(0.5919, 0.6653)0.4636(0.4146, 0.5100)0.6346(0.5969, 0.6696)graph_scatterplot
7ATEC40.6064(0.5665, 0.6434)0.4467(0.3967, 0.4941)0.5885(0.5473, 0.6268)graph_scatterplot
8ATEC10.6066(0.5668, 0.6437)0.4439(0.3937, 0.4914)0.5916(0.5506, 0.6297)graph_scatterplot
9SNR0.6127(0.5733, 0.6493)0.4513(0.4015, 0.4984)0.5746(0.5324, 0.6139)graph_scatterplot
10mBLEU0.2280(0.1696, 0.2848)0.1560(0.0962, 0.2147)0.1948(0.1357, 0.2526)graph_scatterplot
114-GRR0.6430(0.6059, 0.6773)0.4700(0.4213, 0.5160)0.5635(0.5205, 0.6036)graph_scatterplot
12ATEC20.6021(0.5619, 0.6395)0.4414(0.3911, 0.4891)0.5880(0.5468, 0.6264)graph_scatterplot
13SEPIA10.6543(0.6181, 0.6877)0.4838(0.4359, 0.5290)0.6314(0.5934, 0.6665)graph_scatterplot
14ULCopt0.7151(0.6841, 0.7436)0.5345(0.4897, 0.5766)0.6932(0.6602, 0.7235)graph_scatterplot
15EDPM0.7047(0.6728, 0.7341)0.5251(0.4797, 0.5678)0.6975(0.6649, 0.7274)graph_scatterplot
16mTER0.0056(-0.0552, 0.0663)0.0045(-0.0563, 0.0653)-0.0951(-0.1550, -0.0345)graph_scatterplot
17BLEU-40.6433(0.6062, 0.6775)0.4680(0.4192, 0.5141)0.6008(0.5605, 0.6383)graph_scatterplot
18METEOR-v0.60.7268(0.6968, 0.7542)0.5451(0.5010, 0.5865)0.7208(0.6903, 0.7488)graph_scatterplot
19BadgerLite0.4582(0.4088, 0.5049)0.3305(0.2753, 0.3835)0.3490(0.2944, 0.4012)graph_scatterplot
20METEOR-ranking0.7135(0.6823, 0.7421)0.5352(0.4904, 0.5772)0.6872(0.6537, 0.7180)graph_scatterplot
21LET0.6187(0.5797, 0.6548)0.4610(0.4118, 0.5075)0.6033(0.5632, 0.6406)graph_scatterplot
22DP-Or0.5316(0.4865, 0.5738)0.3985(0.3461, 0.4484)0.5292(0.4840, 0.5716)graph_scatterplot
23ATEC30.6019(0.5617, 0.6393)0.4413(0.3910, 0.4889)0.5887(0.5475, 0.6270)graph_scatterplot
24BLEU-v120.4424(0.3921, 0.4900)0.3481(0.2936, 0.4004)0.4665(0.4176, 0.5127)graph_scatterplot
25BEwT-E0.3820(0.3288, 0.4327)0.2887(0.2320, 0.3434)0.4146(0.3630, 0.4637)graph_scatterplot
26DR-Or0.5990(0.5586, 0.6366)0.4395(0.3891, 0.4872)0.5913(0.5503, 0.6295)graph_scatterplot
27BleuSP0.6706(0.6358, 0.7028)0.4947(0.4473, 0.5392)0.6487(0.6120, 0.6825)graph_scatterplot
28SVM-Rank0.6909(0.6577, 0.7213)0.5113(0.4649, 0.5548)0.6697(0.6348, 0.7019)graph_scatterplot
29BLEU-10.6343(0.5966, 0.6693)0.4678(0.4189, 0.5139)0.6368(0.5992, 0.6716)graph_scatterplot
30Bleu-sbp0.4332(0.3825, 0.4813)0.3414(0.2865, 0.3939)0.4587(0.4094, 0.5054)graph_scatterplot
31invWer-0.6843(-0.7153, -0.6506)-0.5073(-0.5511, -0.4607)-0.6410(-0.6755, -0.6038)graph_scatterplot
32BLEU-v11b0.4332(0.3825, 0.4812)0.3414(0.2865, 0.3939)0.4587(0.4094, 0.5054)graph_scatterplot
33SR-Or0.4953(0.4480, 0.5398)0.3543(0.3000, 0.4063)0.4738(0.4253, 0.5196)graph_scatterplot
34Badger0.3121(0.2562, 0.3659)0.2203(0.1617, 0.2773)0.2829(0.2260, 0.3379)graph_scatterplot
35Meteor-v0.70.7249(0.6948, 0.7525)0.5451(0.5009, 0.5864)0.7243(0.6941, 0.7520)graph_scatterplot
36MaxSim0.5907(0.5497, 0.6289)0.4357(0.3851, 0.4837)0.6019(0.5617, 0.6393)graph_scatterplot
37TERp-0.7407(-0.7670, -0.7120)-0.5609(-0.6011, -0.5178)-0.7344(-0.7612, -0.7051)graph_scatterplot

37 metrics (including 7 baseline metrics)
1041 data points (total number of segments used)