Go Back

Correlation Results

Current Conditions

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

Subdivisions

By track:

Ranking

Single Reference Track
RankMetric NameSpearman's RhoKendall's TauPearson's RGraphs
Value95% confidence intervalValue95% confidence intervalValue95% confidence interval
1SEPIA2-0.7414(-0.8914, -0.4447)-0.6105(-0.8291, -0.2302)-0.8420(-0.9358, -0.6368)graph_scatterplot
2CDer0.7368(0.4367, 0.8894)0.6000(0.2144, 0.8238)0.8499(0.6529, 0.9392)graph_scatterplot
3ULCh-0.8361(-0.9333, -0.6247)-0.6947(-0.8698, -0.3642)-0.9024(-0.9611, -0.7656)graph_scatterplot
4TER-v0.7.250.6857(0.3491, 0.8656)0.5263(0.1092, 0.7858)0.8758(0.7075, 0.9501)graph_scatterplot
5DP-Orp-0.8842(-0.9536, -0.7256)-0.7368(-0.8894, -0.4367)-0.8826(-0.9529, -0.7221)graph_scatterplot
6NIST-v11b-0.7579(-0.8989, -0.4745)-0.6211(-0.8343, -0.2462)-0.8517(-0.9400, -0.6567)graph_scatterplot
7ATEC4-0.6752(-0.8606, -0.3318)-0.5895(-0.8185, -0.1988)-0.7821(-0.9097, -0.5192)graph_scatterplot
8ATEC1-0.6692(-0.8577, -0.3220)-0.5684(-0.8078, -0.1682)-0.7792(-0.9085, -0.5138)graph_scatterplot
9mBLEU-0.6980(-0.8714, -0.3697)-0.5541(-0.8004, -0.1478)-0.8210(-0.9268, -0.5945)graph_scatterplot
10SNR-0.7850(-0.9110, -0.5247)-0.6526(-0.8497, -0.2954)-0.8657(-0.9459, -0.6860)graph_scatterplot
114-GRR-0.6602(-0.8534, -0.3074)-0.5158(-0.7802, -0.0949)-0.8554(-0.9415, -0.6644)graph_scatterplot
12ATEC2-0.6752(-0.8606, -0.3318)-0.5895(-0.8185, -0.1988)-0.7778(-0.9079, -0.5113)graph_scatterplot
13SEPIA1-0.7414(-0.8914, -0.4447)-0.6000(-0.8238, -0.2144)-0.8652(-0.9456, -0.6849)graph_scatterplot
14ULCopt-0.7820(-0.9097, -0.5190)-0.6526(-0.8497, -0.2954)-0.8659(-0.9459, -0.6863)graph_scatterplot
15mTER0.6301(0.2601, 0.8387)0.5053(0.0808, 0.7746)0.8394(0.6315, 0.9347)graph_scatterplot
16EDPM-0.7985(-0.9170, -0.5505)-0.6632(-0.8548, -0.3123)-0.8953(-0.9582, -0.7498)graph_scatterplot
17BLEU-4-0.7654(-0.9023, -0.4883)-0.6316(-0.8395, -0.2624)-0.8687(-0.9471, -0.6923)graph_scatterplot
18METEOR-v0.6-0.7579(-0.8989, -0.4745)-0.6211(-0.8343, -0.2462)-0.8467(-0.9378, -0.6464)graph_scatterplot
19RTE-MT-0.7774(-0.9077, -0.5106)-0.6316(-0.8395, -0.2624)-0.9009(-0.9605, -0.7622)graph_scatterplot
20BadgerLite-0.7444(-0.8928, -0.4501)-0.5895(-0.8185, -0.1988)-0.8838(-0.9534, -0.7247)graph_scatterplot
21METEOR-ranking-0.7383(-0.8901, -0.4394)-0.5895(-0.8185, -0.1988)-0.8408(-0.9353, -0.6342)graph_scatterplot
22LET-0.7684(-0.9037, -0.4938)-0.6000(-0.8238, -0.2144)-0.8595(-0.9433, -0.6730)graph_scatterplot
23DP-Or-0.8226(-0.9275, -0.5975)-0.6842(-0.8649, -0.3466)-0.9033(-0.9615, -0.7676)graph_scatterplot
24ATEC3-0.7461(-0.8936, -0.4533)-0.6174(-0.8325, -0.2406)-0.8416(-0.9357, -0.6359)graph_scatterplot
25BLEU-v12-0.7383(-0.8901, -0.4394)-0.5895(-0.8185, -0.1988)-0.8735(-0.9491, -0.7024)graph_scatterplot
26BEwT-E-0.7654(-0.9023, -0.4883)-0.6421(-0.8446, -0.2788)-0.8404(-0.9351, -0.6335)graph_scatterplot
27RTE-0.7925(-0.9144, -0.5390)-0.6526(-0.8497, -0.2954)-0.8952(-0.9582, -0.7497)graph_scatterplot
28DR-Or-0.7504(-0.8955, -0.4609)-0.6105(-0.8291, -0.2302)-0.8479(-0.9384, -0.6489)graph_scatterplot
29BleuSP-0.7609(-0.9003, -0.4800)-0.6211(-0.8343, -0.2462)-0.8794(-0.9516, -0.7152)graph_scatterplot
30SVM-Rank-0.8030(-0.9190, -0.5592)-0.6737(-0.8599, -0.3293)-0.8576(-0.9424, -0.6689)graph_scatterplot
31BLEU-1-0.7459(-0.8935, -0.4528)-0.6211(-0.8343, -0.2462)-0.8490(-0.9388, -0.6510)graph_scatterplot
32Bleu-sbp-0.7263(-0.8845, -0.4182)-0.6000(-0.8238, -0.2144)-0.8702(-0.9478, -0.6956)graph_scatterplot
33invWer0.6902(0.3566, 0.8677)0.5474(0.1384, 0.7969)0.8739(0.7035, 0.9493)graph_scatterplot
34BLEU-v11b-0.7534(-0.8969, -0.4663)-0.6105(-0.8291, -0.2302)-0.8667(-0.9463, -0.6881)graph_scatterplot
35SR-Or-0.8526(-0.9404, -0.6586)-0.6842(-0.8649, -0.3466)-0.9186(-0.9677, -0.8022)graph_scatterplot
36Badger-0.6887(-0.8670, -0.3541)-0.5368(-0.7914, -0.1237)-0.8402(-0.9350, -0.6329)graph_scatterplot
37Meteor-v0.7-0.7564(-0.8983, -0.4718)-0.6105(-0.8291, -0.2302)-0.8418(-0.9358, -0.6364)graph_scatterplot
38MaxSim-0.7323(-0.8873, -0.4288)-0.6000(-0.8238, -0.2144)-0.8039(-0.9193, -0.5608)graph_scatterplot
39TERp0.7263(0.4182, 0.8845)0.5789(0.1834, 0.8131)0.8161(0.5847, 0.9247)graph_scatterplot

39 metrics (including 7 baseline metrics)
20 data points (total number of systems used)