Single Reference Track
| 1 | BadgerLite | 0.6373 | (0.5572, 0.7057) | 0.4654 | (0.3621, 0.5575) | 0.6143 | (0.5304, 0.6862) | graph_scatterplot |
| 2 | METEOR-ranking | 0.7652 | (0.7082, 0.8122) | 0.5824 | (0.4938, 0.6590) | 0.7409 | (0.6791, 0.7922) | graph_scatterplot |
| 3 | LET | 0.7140 | (0.6471, 0.7700) | 0.5459 | (0.4523, 0.6277) | 0.7646 | (0.7075, 0.8117) | graph_scatterplot |
| 4 | SEPIA2 | 0.7344 | (0.6714, 0.7869) | 0.5703 | (0.4800, 0.6486) | 0.7734 | (0.7182, 0.8190) | graph_scatterplot |
| 5 | CDer | -0.7189 | (-0.7740, -0.6529) | -0.5580 | (-0.6381, -0.4660) | -0.7994 | (-0.8402, -0.7496) | graph_scatterplot |
| 6 | ATEC3 | 0.5068 | (0.4082, 0.5937) | 0.3646 | (0.2517, 0.4678) | 0.5958 | (0.5092, 0.6705) | graph_scatterplot |
| 7 | TER-v0.7.25 | -0.6854 | (-0.7462, -0.6134) | -0.5325 | (-0.6160, -0.4371) | -0.7691 | (-0.8155, -0.7130) | graph_scatterplot |
| 8 | BLEU-v12 | 0.7528 | (0.6934, 0.8021) | 0.5904 | (0.5031, 0.6659) | 0.7093 | (0.6416, 0.7661) | graph_scatterplot |
| 9 | BleuSP | 0.7559 | (0.6970, 0.8046) | 0.5931 | (0.5061, 0.6681) | 0.7384 | (0.6762, 0.7902) | graph_scatterplot |
| 10 | NIST-v11b | 0.7227 | (0.6574, 0.7772) | 0.5623 | (0.4709, 0.6417) | 0.7590 | (0.7008, 0.8072) | graph_scatterplot |
| 11 | SVM-Rank | 0.7729 | (0.7175, 0.8186) | 0.6022 | (0.5165, 0.6759) | 0.7844 | (0.7314, 0.8279) | graph_scatterplot |
| 12 | BLEU-1 | 0.7114 | (0.6440, 0.7678) | 0.5529 | (0.4602, 0.6336) | 0.7768 | (0.7223, 0.8218) | graph_scatterplot |
| 13 | ATEC4 | 0.5393 | (0.4448, 0.6219) | 0.3917 | (0.2810, 0.4920) | 0.6291 | (0.5476, 0.6987) | graph_scatterplot |
| 14 | Bleu-sbp | 0.7523 | (0.6928, 0.8017) | 0.5909 | (0.5036, 0.6663) | 0.6968 | (0.6268, 0.7557) | graph_scatterplot |
| 15 | ATEC1 | 0.5349 | (0.4399, 0.6182) | 0.3873 | (0.2763, 0.4881) | 0.6235 | (0.5412, 0.6941) | graph_scatterplot |
| 16 | invWer | -0.6884 | (-0.7487, -0.6169) | -0.5365 | (-0.6195, -0.4417) | -0.7781 | (-0.8228, -0.7238) | graph_scatterplot |
| 17 | SNR | 0.7293 | (0.6654, 0.7827) | 0.5460 | (0.4524, 0.6277) | 0.8071 | (0.7589, 0.8465) | graph_scatterplot |
| 18 | mBLEU | 0.7503 | (0.6904, 0.8000) | 0.5839 | (0.4956, 0.6603) | 0.7003 | (0.6309, 0.7586) | graph_scatterplot |
| 19 | 4-GRR | 0.7528 | (0.6934, 0.8021) | 0.5926 | (0.5055, 0.6677) | 0.7287 | (0.6646, 0.7822) | graph_scatterplot |
| 20 | BLEU-v11b | 0.7458 | (0.6849, 0.7963) | 0.5837 | (0.4953, 0.6601) | 0.6968 | (0.6268, 0.7557) | graph_scatterplot |
| 21 | Badger | 0.6443 | (0.5653, 0.7116) | 0.4719 | (0.3693, 0.5632) | 0.6238 | (0.5414, 0.6942) | graph_scatterplot |
| 22 | ATEC2 | 0.5365 | (0.4416, 0.6195) | 0.3883 | (0.2774, 0.4890) | 0.6246 | (0.5424, 0.6950) | graph_scatterplot |
| 23 | SEPIA1 | 0.7505 | (0.6906, 0.8001) | 0.5855 | (0.4974, 0.6616) | 0.7233 | (0.6582, 0.7777) | graph_scatterplot |
| 24 | Meteor-v0.7 | 0.7758 | (0.7210, 0.8209) | 0.6060 | (0.5209, 0.6792) | 0.6784 | (0.6051, 0.7403) | graph_scatterplot |
| 25 | MaxSim | 0.6392 | (0.5593, 0.7073) | 0.4645 | (0.3611, 0.5567) | 0.6892 | (0.6178, 0.7493) | graph_scatterplot |
| 26 | mTER | -0.6712 | (-0.7343, -0.5967) | -0.5183 | (-0.6037, -0.4211) | -0.7650 | (-0.8120, -0.7080) | graph_scatterplot |
| 27 | BLEU-4 | 0.7480 | (0.6876, 0.7981) | 0.5865 | (0.4985, 0.6625) | 0.6961 | (0.6260, 0.7551) | graph_scatterplot |
| 28 | METEOR-v0.6 | 0.7222 | (0.6569, 0.7768) | 0.5444 | (0.4506, 0.6263) | 0.7825 | (0.7291, 0.8264) | graph_scatterplot |
| 29 | TERp | -0.7702 | (-0.8164, -0.7143) | -0.5926 | (-0.6677, -0.5055) | -0.7921 | (-0.8342, -0.7407) | graph_scatterplot |
29 metrics (including 7 baseline metrics)
249 data points (total number of documents used)
|
Multiple References Track
| 1 | BadgerLite | 0.4835 | (0.3714, 0.5818) | 0.3583 | (0.2330, 0.4719) | 0.5729 | (0.4733, 0.6581) | graph_scatterplot |
| 2 | METEOR-ranking | 0.6307 | (0.5406, 0.7065) | 0.4620 | (0.3472, 0.5631) | 0.7187 | (0.6454, 0.7789) | graph_scatterplot |
| 3 | LET | 0.5599 | (0.4582, 0.6470) | 0.4201 | (0.3007, 0.5266) | 0.6867 | (0.6070, 0.7527) | graph_scatterplot |
| 4 | SEPIA2 | 0.5908 | (0.4940, 0.6731) | 0.4352 | (0.3174, 0.5398) | 0.7105 | (0.6355, 0.7722) | graph_scatterplot |
| 5 | CDer | -0.6027 | (-0.6832, -0.5079) | -0.4415 | (-0.5453, -0.3244) | -0.7362 | (-0.7931, -0.6666) | graph_scatterplot |
| 6 | ATEC3 | 0.4512 | (0.3352, 0.5538) | 0.3160 | (0.1874, 0.4339) | 0.5514 | (0.4485, 0.6399) | graph_scatterplot |
| 7 | TER-v0.7.25 | -0.5598 | (-0.6470, -0.4581) | -0.4062 | (-0.5144, -0.2854) | -0.7146 | (-0.7755, -0.6404) | graph_scatterplot |
| 8 | BLEU-v12 | 0.5553 | (0.4530, 0.6432) | 0.4137 | (0.2936, 0.5209) | 0.6875 | (0.6080, 0.7534) | graph_scatterplot |
| 9 | BleuSP | 0.6268 | (0.5360, 0.7032) | 0.4629 | (0.3482, 0.5639) | 0.7397 | (0.6708, 0.7959) | graph_scatterplot |
| 10 | NIST-v11b | 0.5622 | (0.4609, 0.6490) | 0.4114 | (0.2911, 0.5189) | 0.7025 | (0.6259, 0.7657) | graph_scatterplot |
| 11 | SVM-Rank | 0.6199 | (0.5280, 0.6975) | 0.4549 | (0.3392, 0.5569) | 0.7417 | (0.6733, 0.7975) | graph_scatterplot |
| 12 | BLEU-1 | 0.5390 | (0.4343, 0.6293) | 0.3955 | (0.2736, 0.5049) | 0.6835 | (0.6031, 0.7501) | graph_scatterplot |
| 13 | Bleu-sbp | 0.5727 | (0.4730, 0.6579) | 0.4218 | (0.3025, 0.5281) | 0.6977 | (0.6201, 0.7617) | graph_scatterplot |
| 14 | ATEC4 | 0.4922 | (0.3812, 0.5893) | 0.3488 | (0.2227, 0.4634) | 0.5864 | (0.4888, 0.6694) | graph_scatterplot |
| 15 | invWer | -0.5925 | (-0.6746, -0.4960) | -0.4321 | (-0.5371, -0.3140) | -0.7262 | (-0.7850, -0.6544) | graph_scatterplot |
| 16 | ATEC1 | 0.4807 | (0.3682, 0.5793) | 0.3412 | (0.2145, 0.4566) | 0.5772 | (0.4782, 0.6617) | graph_scatterplot |
| 17 | SNR | 0.6304 | (0.5402, 0.7062) | 0.4557 | (0.3402, 0.5577) | 0.7065 | (0.6307, 0.7690) | graph_scatterplot |
| 18 | mBLEU | 0.5457 | (0.4420, 0.6351) | 0.3976 | (0.2759, 0.5068) | 0.6620 | (0.5776, 0.7325) | graph_scatterplot |
| 19 | BLEU-v11b | 0.5674 | (0.4669, 0.6534) | 0.4195 | (0.3000, 0.5261) | 0.6953 | (0.6172, 0.7598) | graph_scatterplot |
| 20 | 4-GRR | 0.6077 | (0.5136, 0.6873) | 0.4438 | (0.3269, 0.5473) | 0.7308 | (0.6600, 0.7887) | graph_scatterplot |
| 21 | Badger | 0.4877 | (0.3760, 0.5854) | 0.3539 | (0.2282, 0.4679) | 0.5841 | (0.4863, 0.6675) | graph_scatterplot |
| 22 | ATEC2 | 0.4828 | (0.3705, 0.5811) | 0.3416 | (0.2149, 0.4570) | 0.5781 | (0.4793, 0.6624) | graph_scatterplot |
| 23 | SEPIA1 | 0.5983 | (0.5027, 0.6794) | 0.4423 | (0.3252, 0.5460) | 0.7094 | (0.6342, 0.7713) | graph_scatterplot |
| 24 | Meteor-v0.7 | 0.6233 | (0.5319, 0.7003) | 0.4605 | (0.3456, 0.5619) | 0.7038 | (0.6274, 0.7667) | graph_scatterplot |
| 25 | MaxSim | 0.5039 | (0.3943, 0.5993) | 0.3582 | (0.2329, 0.4718) | 0.5958 | (0.4998, 0.6773) | graph_scatterplot |
| 26 | mTER | -0.5819 | (-0.6656, -0.4836) | -0.4385 | (-0.5427, -0.3211) | -0.7214 | (-0.7810, -0.6486) | graph_scatterplot |
| 27 | BLEU-4 | 0.5746 | (0.4752, 0.6595) | 0.4239 | (0.3049, 0.5299) | 0.6986 | (0.6212, 0.7625) | graph_scatterplot |
| 28 | METEOR-v0.6 | 0.5977 | (0.5021, 0.6790) | 0.4334 | (0.3154, 0.5383) | 0.7303 | (0.6594, 0.7883) | graph_scatterplot |
| 29 | TERp | -0.6239 | (-0.7008, -0.5326) | -0.4505 | (-0.5531, -0.3343) | -0.7403 | (-0.7964, -0.6716) | graph_scatterplot |
29 metrics (including 7 baseline metrics)
206 data points (total number of documents used)
|
