Single Reference Track
| 1 | SEPIA2 | 0.8620 | (0.7967, 0.9073) | 0.6742 | (0.5420, 0.7738) | 0.8501 | (0.7799, 0.8992) | graph_category graph_category_2 graph_scatterplot |
| 2 | CDer | -0.9037 | (-0.9359, -0.8567) | -0.7360 | (-0.8187, -0.6232) | -0.8805 | (-0.9201, -0.8232) | graph_category graph_category_2 graph_scatterplot |
| 3 | ULCh | 0.5422 | (0.3765, 0.6743) | 0.4070 | (0.2172, 0.5672) | 0.5439 | (0.3785, 0.6756) | graph_category graph_category_2 graph_scatterplot |
| 4 | TER-v0.7.25 | -0.8877 | (-0.9250, -0.8336) | -0.7133 | (-0.8024, -0.5932) | -0.8542 | (-0.9020, -0.7857) | graph_category graph_category_2 graph_scatterplot |
| 5 | DP-Orp | 0.4712 | (0.2916, 0.6188) | 0.3718 | (0.1773, 0.5384) | 0.4962 | (0.3212, 0.6385) | graph_category graph_category_2 graph_scatterplot |
| 6 | NIST-v11b | 0.8775 | (0.8190, 0.9180) | 0.6915 | (0.5646, 0.7865) | 0.8534 | (0.7845, 0.9014) | graph_category graph_category_2 graph_scatterplot |
| 7 | ATEC4 | 0.8315 | (0.7537, 0.8863) | 0.6353 | (0.4922, 0.7450) | 0.8099 | (0.7237, 0.8712) | graph_category graph_category_2 graph_scatterplot |
| 8 | ATEC1 | 0.8375 | (0.7622, 0.8905) | 0.6444 | (0.5037, 0.7517) | 0.8148 | (0.7306, 0.8747) | graph_category graph_category_2 graph_scatterplot |
| 9 | mBLEU | 0.6909 | (0.5637, 0.7860) | 0.5694 | (0.4098, 0.6952) | 0.5470 | (0.3822, 0.6780) | graph_category graph_category_2 graph_scatterplot |
| 10 | SNR | 0.5617 | (0.4003, 0.6893) | 0.4244 | (0.2371, 0.5813) | 0.5189 | (0.3483, 0.6562) | graph_category graph_category_2 graph_scatterplot |
| 11 | 4-GRR | 0.8550 | (0.7868, 0.9025) | 0.6680 | (0.5341, 0.7693) | 0.8304 | (0.7523, 0.8855) | graph_category graph_category_2 graph_scatterplot |
| 12 | ATEC2 | 0.8380 | (0.7629, 0.8908) | 0.6466 | (0.5065, 0.7534) | 0.8157 | (0.7318, 0.8753) | graph_category graph_category_2 graph_scatterplot |
| 13 | SEPIA1 | 0.8689 | (0.8066, 0.9121) | 0.6849 | (0.5559, 0.7817) | 0.8481 | (0.7771, 0.8978) | graph_category graph_category_2 graph_scatterplot |
| 14 | ULCopt | 0.5591 | (0.3970, 0.6873) | 0.4244 | (0.2371, 0.5813) | 0.5285 | (0.3599, 0.6637) | graph_category graph_category_2 graph_scatterplot |
| 15 | mTER | -0.6841 | (-0.7811, -0.5549) | -0.5495 | (-0.6800, -0.3854) | -0.4223 | (-0.5796, -0.2347) | graph_category graph_category_2 graph_scatterplot |
| 16 | EDPM | 0.8797 | (0.8220, 0.9195) | 0.6874 | (0.5592, 0.7835) | 0.8510 | (0.7811, 0.8998) | graph_category graph_category_2 graph_scatterplot |
| 17 | BLEU-4 | 0.8423 | (0.7689, 0.8937) | 0.6512 | (0.5124, 0.7568) | 0.8221 | (0.7407, 0.8798) | graph_category graph_category_2 graph_scatterplot |
| 18 | METEOR-v0.6 | 0.8876 | (0.8335, 0.9249) | 0.7002 | (0.5759, 0.7928) | 0.8701 | (0.8082, 0.9129) | graph_category graph_category_2 graph_scatterplot |
| 19 | RTE-MT | 0.6960 | (0.5705, 0.7898) | 0.5271 | (0.3581, 0.6626) | 0.7004 | (0.5761, 0.7930) | graph_category graph_category_2 graph_scatterplot |
| 20 | BadgerLite | 0.6902 | (0.5629, 0.7856) | 0.4990 | (0.3244, 0.6407) | 0.7212 | (0.6036, 0.8081) | graph_category graph_category_2 graph_scatterplot |
| 21 | METEOR-ranking | 0.8906 | (0.8376, 0.9269) | 0.7074 | (0.5853, 0.7981) | 0.8729 | (0.8123, 0.9148) | graph_category graph_category_2 graph_scatterplot |
| 22 | LET | 0.8793 | (0.8214, 0.9192) | 0.6823 | (0.5526, 0.7798) | 0.8547 | (0.7864, 0.9023) | graph_category graph_category_2 graph_scatterplot |
| 23 | DP-Or | 0.5826 | (0.4260, 0.7053) | 0.4501 | (0.2668, 0.6019) | 0.6339 | (0.4904, 0.7440) | graph_category graph_category_2 graph_scatterplot |
| 24 | ATEC3 | 0.8740 | (0.8139, 0.9156) | 0.6830 | (0.5535, 0.7803) | 0.8505 | (0.7804, 0.8994) | graph_category graph_category_2 graph_scatterplot |
| 25 | BLEU-v12 | 0.8567 | (0.7892, 0.9037) | 0.6709 | (0.5378, 0.7714) | 0.8335 | (0.7566, 0.8877) | graph_category graph_category_2 graph_scatterplot |
| 26 | BEwT-E | 0.7776 | (0.6794, 0.8485) | 0.6272 | (0.4818, 0.7389) | 0.7376 | (0.6254, 0.8199) | graph_category graph_category_2 graph_scatterplot |
| 27 | RTE | 0.6226 | (0.4761, 0.7355) | 0.4545 | (0.2720, 0.6055) | 0.6427 | (0.5016, 0.7505) | graph_category graph_category_2 graph_scatterplot |
| 28 | DR-Or | 0.5009 | (0.3267, 0.6422) | 0.3821 | (0.1889, 0.5469) | 0.5284 | (0.3598, 0.6637) | graph_category graph_category_2 graph_scatterplot |
| 29 | BleuSP | 0.8465 | (0.7748, 0.8967) | 0.6542 | (0.5163, 0.7591) | 0.8250 | (0.7447, 0.8818) | graph_category graph_category_2 graph_scatterplot |
| 30 | SVM-Rank | 0.8845 | (0.8289, 0.9228) | 0.7038 | (0.5806, 0.7955) | 0.8495 | (0.7791, 0.8988) | graph_category graph_category_2 graph_scatterplot |
| 31 | BLEU-1 | 0.8608 | (0.7951, 0.9066) | 0.6699 | (0.5365, 0.7706) | 0.8453 | (0.7731, 0.8959) | graph_category graph_category_2 graph_scatterplot |
| 32 | Bleu-sbp | 0.8679 | (0.8052, 0.9114) | 0.6793 | (0.5486, 0.7775) | 0.8382 | (0.7631, 0.8909) | graph_category graph_category_2 graph_scatterplot |
| 33 | invWer | -0.8921 | (-0.9280, -0.8399) | -0.7222 | (-0.8088, -0.6049) | -0.8530 | (-0.9012, -0.7841) | graph_category graph_category_2 graph_scatterplot |
| 34 | BLEU-v11b | 0.8480 | (0.7769, 0.8977) | 0.6554 | (0.5179, 0.7600) | 0.8239 | (0.7432, 0.8810) | graph_category graph_category_2 graph_scatterplot |
| 35 | SR-Or | 0.5096 | (0.3371, 0.6490) | 0.3783 | (0.1846, 0.5438) | 0.5371 | (0.3702, 0.6704) | graph_category graph_category_2 graph_scatterplot |
| 36 | Badger | 0.6629 | (0.5274, 0.7655) | 0.4918 | (0.3159, 0.6350) | 0.7061 | (0.5837, 0.7972) | graph_category graph_category_2 graph_scatterplot |
| 37 | Meteor-v0.7 | 0.8968 | (0.8466, 0.9311) | 0.7125 | (0.5920, 0.8018) | 0.8745 | (0.8146, 0.9159) | graph_category graph_category_2 graph_scatterplot |
| 38 | MaxSim | 0.5879 | (0.4326, 0.7093) | 0.4499 | (0.2667, 0.6018) | 0.6172 | (0.4693, 0.7314) | graph_category graph_category_2 graph_scatterplot |
| 39 | TERp | -0.8685 | (-0.9118, -0.8060) | -0.6803 | (-0.7783, -0.5499) | -0.8493 | (-0.8986, -0.7788) | graph_category graph_category_2 graph_scatterplot |
39 metrics (including 7 baseline metrics)
89 data points (total number of systems used)
|
Multiple References Track
| 1 | SEPIA2 | 0.9307 | (0.8836, 0.9592) | 0.7764 | (0.6437, 0.8638) | 0.9158 | (0.8593, 0.9502) | graph_category graph_category_2 graph_scatterplot |
| 2 | CDer | -0.9167 | (-0.9508, -0.8607) | -0.7616 | (-0.8543, -0.6220) | -0.9038 | (-0.9430, -0.8398) | graph_category graph_category_2 graph_scatterplot |
| 3 | ULCh | 0.1258 | (-0.1443, 0.3785) | 0.2135 | (-0.0549, 0.4531) | -0.0402 | (-0.3023, 0.2275) | graph_category graph_category_2 graph_scatterplot |
| 4 | TER-v0.7.25 | -0.8952 | (-0.9378, -0.8262) | -0.7239 | (-0.8298, -0.5676) | -0.8676 | (-0.9209, -0.7824) | graph_category graph_category_2 graph_scatterplot |
| 5 | DP-Orp | 0.0848 | (-0.1846, 0.3424) | 0.1886 | (-0.0807, 0.4323) | -0.1381 | (-0.3891, 0.1321) | graph_category graph_category_2 graph_scatterplot |
| 6 | NIST-v11b | 0.9314 | (0.8847, 0.9596) | 0.7747 | (0.6411, 0.8627) | 0.9117 | (0.8526, 0.9478) | graph_category graph_category_2 graph_scatterplot |
| 7 | ATEC4 | 0.9001 | (0.8339, 0.9407) | 0.7428 | (0.5946, 0.8421) | 0.8937 | (0.8237, 0.9369) | graph_category graph_category_2 graph_scatterplot |
| 8 | ATEC1 | 0.9017 | (0.8366, 0.9417) | 0.7441 | (0.5966, 0.8430) | 0.8966 | (0.8284, 0.9386) | graph_category graph_category_2 graph_scatterplot |
| 9 | SNR | 0.0628 | (-0.2059, 0.3228) | 0.1313 | (-0.1388, 0.3833) | -0.0558 | (-0.3164, 0.2127) | graph_category graph_category_2 graph_scatterplot |
| 10 | mBLEU | 0.8526 | (0.7590, 0.9117) | 0.7019 | (0.5365, 0.8154) | 0.7786 | (0.6469, 0.8652) | graph_category graph_category_2 graph_scatterplot |
| 11 | 4-GRR | 0.8356 | (0.7328, 0.9012) | 0.6727 | (0.4959, 0.7960) | 0.8127 | (0.6978, 0.8868) | graph_category graph_category_2 graph_scatterplot |
| 12 | ATEC2 | 0.9021 | (0.8371, 0.9420) | 0.7495 | (0.6044, 0.8465) | 0.8940 | (0.8242, 0.9370) | graph_category graph_category_2 graph_scatterplot |
| 13 | SEPIA1 | 0.9031 | (0.8388, 0.9426) | 0.7508 | (0.6063, 0.8474) | 0.9004 | (0.8344, 0.9409) | graph_category graph_category_2 graph_scatterplot |
| 14 | ULCopt | 0.1146 | (-0.1554, 0.3687) | 0.1892 | (-0.0801, 0.4328) | -0.0485 | (-0.3098, 0.2196) | graph_category graph_category_2 graph_scatterplot |
| 15 | EDPM | 0.9218 | (0.8690, 0.9538) | 0.7684 | (0.6318, 0.8586) | 0.8975 | (0.8298, 0.9392) | graph_category graph_category_2 graph_scatterplot |
| 16 | mTER | -0.8610 | (-0.9169, -0.7721) | -0.6633 | (-0.7896, -0.4830) | -0.7058 | (-0.8180, -0.5421) | graph_category graph_category_2 graph_scatterplot |
| 17 | BLEU-4 | 0.8909 | (0.8192, 0.9351) | 0.7369 | (0.5863, 0.8383) | 0.8690 | (0.7846, 0.9218) | graph_category graph_category_2 graph_scatterplot |
| 18 | METEOR-v0.6 | 0.8457 | (0.7482, 0.9074) | 0.6741 | (0.4978, 0.7969) | 0.8477 | (0.7514, 0.9086) | graph_category graph_category_2 graph_scatterplot |
| 19 | BadgerLite | 0.2450 | (-0.0217, 0.4792) | 0.1596 | (-0.1104, 0.4076) | 0.3042 | (0.0423, 0.5269) | graph_category graph_category_2 graph_scatterplot |
| 20 | METEOR-ranking | 0.8444 | (0.7463, 0.9066) | 0.6700 | (0.4922, 0.7942) | 0.8490 | (0.7533, 0.9094) | graph_category graph_category_2 graph_scatterplot |
| 21 | LET | 0.9335 | (0.8882, 0.9609) | 0.7778 | (0.6457, 0.8647) | 0.9201 | (0.8663, 0.9528) | graph_category graph_category_2 graph_scatterplot |
| 22 | DP-Or | 0.1219 | (-0.1482, 0.3750) | 0.1983 | (-0.0707, 0.4404) | 0.0775 | (-0.1917, 0.3359) | graph_category graph_category_2 graph_scatterplot |
| 23 | ATEC3 | 0.9341 | (0.8892, 0.9612) | 0.7832 | (0.6537, 0.8681) | 0.9234 | (0.8717, 0.9548) | graph_category graph_category_2 graph_scatterplot |
| 24 | BLEU-v12 | 0.9008 | (0.8351, 0.9412) | 0.7481 | (0.6024, 0.8456) | 0.8695 | (0.7853, 0.9221) | graph_category graph_category_2 graph_scatterplot |
| 25 | BEwT-E | 0.9240 | (0.8727, 0.9552) | 0.7764 | (0.6437, 0.8638) | 0.8988 | (0.8319, 0.9400) | graph_category graph_category_2 graph_scatterplot |
| 26 | DR-Or | 0.1207 | (-0.1494, 0.3740) | 0.1967 | (-0.0724, 0.4391) | -0.0073 | (-0.2721, 0.2585) | graph_category graph_category_2 graph_scatterplot |
| 27 | BleuSP | 0.8360 | (0.7334, 0.9014) | 0.6646 | (0.4848, 0.7905) | 0.8488 | (0.7531, 0.9093) | graph_category graph_category_2 graph_scatterplot |
| 28 | SVM-Rank | 0.8247 | (0.7161, 0.8944) | 0.6660 | (0.4867, 0.7915) | 0.8442 | (0.7460, 0.9065) | graph_category graph_category_2 graph_scatterplot |
| 29 | BLEU-1 | 0.9086 | (0.8477, 0.9459) | 0.7329 | (0.5805, 0.8357) | 0.8852 | (0.8102, 0.9317) | graph_category graph_category_2 graph_scatterplot |
| 30 | Bleu-sbp | 0.9113 | (0.8519, 0.9475) | 0.7522 | (0.6083, 0.8482) | 0.8807 | (0.8030, 0.9289) | graph_category graph_category_2 graph_scatterplot |
| 31 | invWer | -0.9120 | (-0.9479, -0.8531) | -0.7508 | (-0.8474, -0.6063) | -0.8992 | (-0.9402, -0.8324) | graph_category graph_category_2 graph_scatterplot |
| 32 | BLEU-v11b | 0.8967 | (0.8285, 0.9387) | 0.7360 | (0.5849, 0.8377) | 0.8661 | (0.7801, 0.9200) | graph_category graph_category_2 graph_scatterplot |
| 33 | SR-Or | 0.1238 | (-0.1463, 0.3767) | 0.2082 | (-0.0604, 0.4487) | -0.0036 | (-0.2687, 0.2619) | graph_category graph_category_2 graph_scatterplot |
| 34 | Badger | 0.1551 | (-0.1149, 0.4038) | 0.0936 | (-0.1761, 0.3502) | 0.1857 | (-0.0837, 0.4298) | graph_category graph_category_2 graph_scatterplot |
| 35 | Meteor-v0.7 | 0.8830 | (0.8067, 0.9304) | 0.7172 | (0.5580, 0.8254) | 0.8739 | (0.7922, 0.9248) | graph_category graph_category_2 graph_scatterplot |
| 36 | MaxSim | 0.1565 | (-0.1135, 0.4050) | 0.2229 | (-0.0451, 0.4609) | 0.1250 | (-0.1451, 0.3778) | graph_category graph_category_2 graph_scatterplot |
| 37 | TERp | -0.8659 | (-0.9199, -0.7798) | -0.7118 | (-0.8219, -0.5504) | -0.8657 | (-0.9198, -0.7795) | graph_category graph_category_2 graph_scatterplot |
37 metrics (including 7 baseline metrics)
55 data points (total number of systems used)
|
