Go Back

Correlation Results

Current Conditions

  • Human Assessment Type: HTER
  • 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
1SEPIA2-0.4886(-0.5106, -0.4659)-0.3527(-0.3782, -0.3268)-0.4395(-0.4629, -0.4155)graph_scatterplot
2CDer0.5447(0.5237, 0.5650)0.3904(0.3652, 0.4150)0.5208(0.4991, 0.5419)graph_scatterplot
3ULCh-0.5266(-0.5475, -0.5050)-0.3784(-0.4032, -0.3529)-0.5035(-0.5251, -0.4813)graph_scatterplot
4TER-v0.7.250.5284(0.5070, 0.5493)0.3786(0.3532, 0.4035)0.5098(0.4877, 0.5312)graph_scatterplot
5DP-Orp-0.3794(-0.4043, -0.3540)-0.2670(-0.2940, -0.2395)-0.3944(-0.4189, -0.3694)graph_scatterplot
6NIST-v11b-0.4732(-0.4957, -0.4501)-0.3417(-0.3674, -0.3155)-0.4748(-0.4972, -0.4518)graph_scatterplot
7ATEC4-0.4062(-0.4304, -0.3814)-0.2965(-0.3230, -0.2695)-0.3897(-0.4143, -0.3645)graph_scatterplot
8ATEC1-0.4133(-0.4373, -0.3886)-0.3017(-0.3282, -0.2748)-0.3954(-0.4198, -0.3703)graph_scatterplot
9mBLEU-0.4447(-0.4680, -0.4208)-0.3128(-0.3391, -0.2861)-0.4250(-0.4488, -0.4007)graph_scatterplot
10SNR-0.5121(-0.5335, -0.4901)-0.3664(-0.3915, -0.3407)-0.4862(-0.5083, -0.4634)graph_scatterplot
114-GRR-0.5163(-0.5375, -0.4944)-0.3692(-0.3943, -0.3435)-0.4884(-0.5104, -0.4657)graph_scatterplot
12ATEC2-0.4109(-0.4350, -0.3862)-0.2998(-0.3262, -0.2728)-0.3914(-0.4160, -0.3663)graph_scatterplot
13SEPIA1-0.4937(-0.5156, -0.4711)-0.3576(-0.3830, -0.3318)-0.4436(-0.4668, -0.4197)graph_scatterplot
14ULCopt-0.5493(-0.5695, -0.5285)-0.3955(-0.4199, -0.3704)-0.5310(-0.5518, -0.5096)graph_scatterplot
15mTER0.4684(0.4452, 0.4910)0.3330(0.3066, 0.3588)0.4387(0.4147, 0.4621)graph_scatterplot
16EDPM-0.5445(-0.5648, -0.5235)-0.3903(-0.4149, -0.3651)-0.5377(-0.5583, -0.5165)graph_scatterplot
17BLEU-4-0.5016(-0.5233, -0.4793)-0.3560(-0.3814, -0.3301)-0.4669(-0.4895, -0.4436)graph_scatterplot
18METEOR-v0.6-0.5123(-0.5337, -0.4904)-0.3710(-0.3961, -0.3454)-0.4883(-0.5104, -0.4657)graph_scatterplot
19RTE-MT-0.5617(-0.5814, -0.5412)-0.3946(-0.4191, -0.3695)-0.5354(-0.5560, -0.5141)graph_scatterplot
20BadgerLite-0.4349(-0.4584, -0.4107)-0.3083(-0.3346, -0.2814)-0.3452(-0.3708, -0.3191)graph_scatterplot
21METEOR-ranking-0.4935(-0.5154, -0.4710)-0.3598(-0.3851, -0.3340)-0.4620(-0.4848, -0.4386)graph_scatterplot
22LET-0.4681(-0.4907, -0.4449)-0.3421(-0.3678, -0.3159)-0.4412(-0.4645, -0.4172)graph_scatterplot
23DP-Or-0.5078(-0.5293, -0.4857)-0.3617(-0.3870, -0.3359)-0.4524(-0.4754, -0.4287)graph_scatterplot
24ATEC3-0.4565(-0.4794, -0.4329)-0.3250(-0.3510, -0.2985)-0.4366(-0.4601, -0.4126)graph_scatterplot
25BLEU-v12-0.4149(-0.4389, -0.3903)-0.3166(-0.3428, -0.2900)-0.4231(-0.4469, -0.3987)graph_scatterplot
26BEwT-E-0.4186(-0.4425, -0.3941)-0.3052(-0.3316, -0.2784)-0.4119(-0.4359, -0.3872)graph_scatterplot
27RTE-0.4852(-0.5073, -0.4624)-0.3372(-0.3629, -0.3109)-0.4555(-0.4784, -0.4319)graph_scatterplot
28DR-Or-0.3817(-0.4065, -0.3563)-0.2733(-0.3002, -0.2459)-0.3945(-0.4190, -0.3695)graph_scatterplot
29BleuSP-0.5295(-0.5503, -0.5080)-0.3743(-0.3993, -0.3488)-0.5006(-0.5223, -0.4783)graph_scatterplot
30SVM-Rank-0.4548(-0.4778, -0.4312)-0.3280(-0.3540, -0.3016)-0.4564(-0.4793, -0.4328)graph_scatterplot
31BLEU-1-0.5127(-0.5340, -0.4907)-0.3661(-0.3912, -0.3404)-0.5000(-0.5217, -0.4777)graph_scatterplot
32Bleu-sbp-0.4095(-0.4337, -0.3848)-0.3129(-0.3391, -0.2861)-0.4172(-0.4412, -0.3927)graph_scatterplot
33invWer0.5303(0.5089, 0.5511)0.3799(0.3545, 0.4048)0.5101(0.4881, 0.5315)graph_scatterplot
34BLEU-v11b-0.4095(-0.4337, -0.3848)-0.3129(-0.3391, -0.2862)-0.4172(-0.4412, -0.3927)graph_scatterplot
35SR-Or-0.3724(-0.3974, -0.3468)-0.2608(-0.2879, -0.2332)-0.3733(-0.3983, -0.3477)graph_scatterplot
36Badger-0.3190(-0.3451, -0.2924)-0.2257(-0.2534, -0.1976)-0.2651(-0.2922, -0.2376)graph_scatterplot
37Meteor-v0.7-0.4940(-0.5159, -0.4715)-0.3613(-0.3866, -0.3355)-0.4655(-0.4882, -0.4422)graph_scatterplot
38MaxSim-0.4761(-0.4985, -0.4531)-0.3497(-0.3752, -0.3237)-0.4574(-0.4803, -0.4338)graph_scatterplot
39TERp0.5511(0.5303, 0.5712)0.3960(0.3710, 0.4205)0.5460(0.5250, 0.5663)graph_scatterplot

39 metrics (including 7 baseline metrics)
4458 data points (total number of segments used)