Go Back

Correlation Results

Current Conditions

  • Human Assessment Type: HTER
  • Target Language: English
  • Correlation Level: document

Subdivisions

By track:

Ranking

Single Reference Track
RankMetric NameSpearman's RhoKendall's TauPearson's RGraphs
Value95% confidence intervalValue95% confidence intervalValue95% confidence interval
1SEPIA2-0.6892(-0.7352, -0.6369)-0.5055(-0.5718, -0.4326)-0.6731(-0.7211, -0.6187)graph_scatterplot
2CDer0.6991(0.6481, 0.7439)0.5153(0.4434, 0.5807)0.6952(0.6437, 0.7405)graph_scatterplot
3ULCh-0.6963(-0.7414, -0.6449)-0.5129(-0.5785, -0.4407)-0.6936(-0.7391, -0.6419)graph_scatterplot
4TER-v0.7.250.6807(0.6273, 0.7278)0.4978(0.4242, 0.5648)0.6873(0.6347, 0.7336)graph_scatterplot
5DP-Orp-0.5788(-0.6376, -0.5132)-0.4143(-0.4887, -0.3339)-0.5191(-0.5841, -0.4475)graph_scatterplot
6NIST-v11b-0.6957(-0.7409, -0.6442)-0.5099(-0.5758, -0.4374)-0.6718(-0.7199, -0.6172)graph_scatterplot
7ATEC4-0.5771(-0.6361, -0.5113)-0.4162(-0.4905, -0.3360)-0.5646(-0.6250, -0.4975)graph_scatterplot
8ATEC1-0.5853(-0.6434, -0.5204)-0.4222(-0.4959, -0.3424)-0.5684(-0.6284, -0.5018)graph_scatterplot
9mBLEU-0.6152(-0.6700, -0.5537)-0.4380(-0.5105, -0.3594)-0.6124(-0.6676, -0.5506)graph_scatterplot
10SNR-0.6958(-0.7410, -0.6443)-0.5075(-0.5736, -0.4348)-0.6811(-0.7281, -0.6277)graph_scatterplot
114-GRR-0.6652(-0.7142, -0.6098)-0.4810(-0.5496, -0.4060)-0.6684(-0.7170, -0.6134)graph_scatterplot
12ATEC2-0.5771(-0.6362, -0.5114)-0.4155(-0.4898, -0.3352)-0.5625(-0.6231, -0.4953)graph_scatterplot
13SEPIA1-0.7011(-0.7456, -0.6504)-0.5146(-0.5800, -0.4425)-0.6905(-0.7363, -0.6383)graph_scatterplot
14ULCopt-0.7074(-0.7511, -0.6575)-0.5220(-0.5867, -0.4506)-0.7014(-0.7459, -0.6507)graph_scatterplot
15mTER0.6193(0.5583, 0.6737)0.4454(0.3674, 0.5172)0.6271(0.5670, 0.6805)graph_scatterplot
16EDPM-0.7284(-0.7694, -0.6814)-0.5410(-0.6038, -0.4715)-0.7245(-0.7660, -0.6770)graph_scatterplot
17BLEU-4-0.6831(-0.7299, -0.6300)-0.4967(-0.5639, -0.4230)-0.6774(-0.7249, -0.6235)graph_scatterplot
18METEOR-v0.6-0.6884(-0.7345, -0.6360)-0.5048(-0.5712, -0.4319)-0.6678(-0.7165, -0.6127)graph_scatterplot
19RTE-MT-0.7160(-0.7586, -0.6673)-0.5320(-0.5957, -0.4617)-0.7136(-0.7565, -0.6646)graph_scatterplot
20BadgerLite-0.6290(-0.6823, -0.5692)-0.4529(-0.5241, -0.3755)-0.5962(-0.6531, -0.5325)graph_scatterplot
21METEOR-ranking-0.6892(-0.7352, -0.6369)-0.5057(-0.5720, -0.4328)-0.6849(-0.7314, -0.6320)graph_scatterplot
22LET-0.6831(-0.7299, -0.6300)-0.4973(-0.5644, -0.4237)-0.6728(-0.7209, -0.6184)graph_scatterplot
23DP-Or-0.6839(-0.7306, -0.6309)-0.5059(-0.5722, -0.4331)-0.6848(-0.7314, -0.6319)graph_scatterplot
24ATEC3-0.6036(-0.6597, -0.5408)-0.4400(-0.5123, -0.3616)-0.5783(-0.6372, -0.5127)graph_scatterplot
25BLEU-v12-0.6839(-0.7305, -0.6308)-0.4965(-0.5636, -0.4228)-0.6798(-0.7270, -0.6263)graph_scatterplot
26BEwT-E-0.6570(-0.7070, -0.6005)-0.4752(-0.5444, -0.3997)-0.6474(-0.6985, -0.5898)graph_scatterplot
27RTE-0.6852(-0.7317, -0.6323)-0.4996(-0.5664, -0.4261)-0.6760(-0.7236, -0.6219)graph_scatterplot
28DR-Or-0.5793(-0.6381, -0.5138)-0.4123(-0.4869, -0.3318)-0.5629(-0.6234, -0.4956)graph_scatterplot
29BleuSP-0.7021(-0.7465, -0.6514)-0.5151(-0.5805, -0.4431)-0.7018(-0.7462, -0.6511)graph_scatterplot
30SVM-Rank-0.6824(-0.7292, -0.6291)-0.4977(-0.5647, -0.4241)-0.6766(-0.7242, -0.6226)graph_scatterplot
31BLEU-1-0.7071(-0.7509, -0.6572)-0.5234(-0.5880, -0.4522)-0.6887(-0.7348, -0.6363)graph_scatterplot
32Bleu-sbp-0.6799(-0.7270, -0.6263)-0.4925(-0.5600, -0.4184)-0.6752(-0.7230, -0.6211)graph_scatterplot
33invWer0.6902(0.6380, 0.7361)0.5069(0.4341, 0.5731)0.6936(0.6418, 0.7390)graph_scatterplot
34BLEU-v11b-0.6816(-0.7286, -0.6283)-0.4942(-0.5616, -0.4203)-0.6771(-0.7246, -0.6232)graph_scatterplot
35SR-Or-0.6568(-0.7068, -0.6003)-0.4821(-0.5506, -0.4072)-0.6689(-0.7174, -0.6140)graph_scatterplot
36Badger-0.5737(-0.6331, -0.5076)-0.4105(-0.4852, -0.3298)-0.5570(-0.6182, -0.4891)graph_scatterplot
37Meteor-v0.7-0.6942(-0.7396, -0.6425)-0.5095(-0.5754, -0.4370)-0.6865(-0.7329, -0.6339)graph_scatterplot
38MaxSim-0.6636(-0.7127, -0.6079)-0.4842(-0.5525, -0.4094)-0.6577(-0.7075, -0.6013)graph_scatterplot
39TERp0.6878(0.6352, 0.7340)0.5067(0.4339, 0.5729)0.6885(0.6361, 0.7346)graph_scatterplot

39 metrics (including 7 baseline metrics)
442 data points (total number of documents used)