Single Reference Track
| 1 | SEPIA2 | 0.7473 | (0.3336, 0.9196) | 0.5641 | (0.0190, 0.8507) | 0.6405 | (0.1384, 0.8807) | graph_scatterplot |
| 2 | CDer | -0.8022 | (-0.9384, -0.4502) | -0.6410 | (-0.8809, -0.1392) | -0.7613 | (-0.9245, -0.3623) | graph_scatterplot |
| 3 | ULCh | 0.5824 | (0.0463, 0.8581) | 0.4359 | (-0.1515, 0.7958) | 0.5482 | (-0.0040, 0.8442) | graph_scatterplot |
| 4 | TER-v0.7.25 | -0.8242 | (-0.9457, -0.5004) | -0.6667 | (-0.8905, -0.1828) | -0.8964 | (-0.9689, -0.6826) | graph_scatterplot |
| 5 | DP-Orp | 0.3956 | (-0.1987, 0.7772) | 0.2821 | (-0.3184, 0.7210) | 0.2467 | (-0.3521, 0.7023) | graph_scatterplot |
| 6 | NIST-v11b | 0.7912 | (0.4259, 0.9347) | 0.5897 | (0.0574, 0.8610) | 0.7626 | (0.3650, 0.9249) | graph_scatterplot |
| 7 | ATEC4 | 0.8022 | (0.4502, 0.9384) | 0.6410 | (0.1392, 0.8809) | 0.7591 | (0.3577, 0.9237) | graph_scatterplot |
| 8 | ATEC1 | 0.8132 | (0.4750, 0.9421) | 0.6667 | (0.1828, 0.8905) | 0.7408 | (0.3207, 0.9174) | graph_scatterplot |
| 9 | mBLEU | -0.0659 | (-0.5953, 0.5033) | 0.0000 | (-0.5510, 0.5510) | 0.4146 | (-0.1768, 0.7860) | graph_scatterplot |
| 10 | SNR | 0.6099 | (0.0887, 0.8689) | 0.4359 | (-0.1515, 0.7958) | 0.6061 | (0.0827, 0.8674) | graph_scatterplot |
| 11 | 4-GRR | 0.8407 | (0.5396, 0.9511) | 0.7179 | (0.2762, 0.9093) | 0.7632 | (0.3662, 0.9252) | graph_scatterplot |
| 12 | ATEC2 | 0.8132 | (0.4750, 0.9421) | 0.6667 | (0.1828, 0.8905) | 0.7513 | (0.3418, 0.9210) | graph_scatterplot |
| 13 | SEPIA1 | 0.7088 | (0.2589, 0.9060) | 0.4872 | (-0.0872, 0.8185) | 0.6054 | (0.0816, 0.8671) | graph_scatterplot |
| 14 | ULCopt | 0.6538 | (0.1608, 0.8857) | 0.5128 | (-0.0532, 0.8294) | 0.6223 | (0.1085, 0.8737) | graph_scatterplot |
| 15 | mTER | -0.5989 | (-0.8646, -0.0715) | -0.4359 | (-0.7958, 0.1515) | -0.5184 | (-0.8318, 0.0457) | graph_scatterplot |
| 16 | EDPM | 0.7967 | (0.4380, 0.9366) | 0.6154 | (0.0974, 0.8710) | 0.7250 | (0.2897, 0.9118) | graph_scatterplot |
| 17 | BLEU-4 | 0.7912 | (0.4259, 0.9347) | 0.5897 | (0.0574, 0.8610) | 0.6920 | (0.2280, 0.8999) | graph_scatterplot |
| 18 | METEOR-v0.6 | 0.5879 | (0.0546, 0.8602) | 0.4615 | (-0.1200, 0.8072) | 0.6255 | (0.1137, 0.8749) | graph_scatterplot |
| 19 | RTE-MT | 0.4835 | (-0.0920, 0.8169) | 0.3333 | (-0.2666, 0.7471) | 0.5146 | (-0.0508, 0.8302) | graph_scatterplot |
| 20 | BadgerLite | 0.4725 | (-0.1061, 0.8121) | 0.3846 | (-0.2111, 0.7720) | 0.4600 | (-0.1219, 0.8065) | graph_scatterplot |
| 21 | METEOR-ranking | 0.6209 | (0.1062, 0.8732) | 0.4872 | (-0.0872, 0.8185) | 0.6197 | (0.1043, 0.8727) | graph_scatterplot |
| 22 | LET | 0.7473 | (0.3336, 0.9196) | 0.5385 | (-0.0178, 0.8402) | 0.6203 | (0.1053, 0.8729) | graph_scatterplot |
| 23 | DP-Or | 0.7143 | (0.2693, 0.9079) | 0.5128 | (-0.0532, 0.8294) | 0.6117 | (0.0915, 0.8696) | graph_scatterplot |
| 24 | ATEC3 | 0.8132 | (0.4750, 0.9421) | 0.6667 | (0.1828, 0.8905) | 0.7614 | (0.3624, 0.9245) | graph_scatterplot |
| 25 | BLEU-v12 | 0.7912 | (0.4259, 0.9347) | 0.5897 | (0.0574, 0.8610) | 0.6948 | (0.2330, 0.9009) | graph_scatterplot |
| 26 | BEwT-E | 0.4505 | (-0.1336, 0.8024) | 0.3333 | (-0.2666, 0.7471) | 0.4151 | (-0.1762, 0.7862) | graph_scatterplot |
| 27 | RTE | 0.4945 | (-0.0776, 0.8216) | 0.3333 | (-0.2666, 0.7471) | 0.5211 | (-0.0420, 0.8329) | graph_scatterplot |
| 28 | DR-Or | 0.4945 | (-0.0776, 0.8216) | 0.3590 | (-0.2394, 0.7597) | 0.5195 | (-0.0441, 0.8323) | graph_scatterplot |
| 29 | BleuSP | 0.7967 | (0.4380, 0.9366) | 0.6154 | (0.0974, 0.8710) | 0.6453 | (0.1464, 0.8825) | graph_scatterplot |
| 30 | SVM-Rank | 0.5879 | (0.0546, 0.8602) | 0.4615 | (-0.1200, 0.8072) | 0.5458 | (-0.0074, 0.8432) | graph_scatterplot |
| 31 | BLEU-1 | 0.7747 | (0.3904, 0.9291) | 0.5897 | (0.0574, 0.8610) | 0.7034 | (0.2489, 0.9040) | graph_scatterplot |
| 32 | Bleu-sbp | 0.7912 | (0.4259, 0.9347) | 0.5897 | (0.0574, 0.8610) | 0.6895 | (0.2233, 0.8990) | graph_scatterplot |
| 33 | invWer | -0.8352 | (-0.9493, -0.5264) | -0.6923 | (-0.9000, -0.2285) | -0.8546 | (-0.9556, -0.5738) | graph_scatterplot |
| 34 | BLEU-v11b | 0.7912 | (0.4259, 0.9347) | 0.5897 | (0.0574, 0.8610) | 0.6906 | (0.2253, 0.8994) | graph_scatterplot |
| 35 | SR-Or | 0.6099 | (0.0887, 0.8689) | 0.4359 | (-0.1515, 0.7958) | 0.5388 | (-0.0173, 0.8403) | graph_scatterplot |
| 36 | Badger | 0.4066 | (-0.1861, 0.7823) | 0.3333 | (-0.2666, 0.7471) | 0.4509 | (-0.1331, 0.8025) | graph_scatterplot |
| 37 | Meteor-v0.7 | 0.6923 | (0.2285, 0.9000) | 0.5385 | (-0.0178, 0.8402) | 0.6723 | (0.1927, 0.8926) | graph_scatterplot |
| 38 | MaxSim | 0.6538 | (0.1608, 0.8857) | 0.4872 | (-0.0872, 0.8185) | 0.6023 | (0.0769, 0.8659) | graph_scatterplot |
| 39 | TERp | -0.8022 | (-0.9384, -0.4502) | -0.6410 | (-0.8809, -0.1392) | -0.7522 | (-0.9214, -0.3437) | graph_scatterplot |
39 metrics (including 7 baseline metrics)
13 data points (total number of systems used)
|
Multiple References Track
| 1 | SEPIA2 | 0.7143 | (0.2693, 0.9079) | 0.5128 | (-0.0532, 0.8294) | 0.7009 | (0.2443, 0.9031) | graph_scatterplot |
| 2 | CDer | -0.7802 | (-0.9310, -0.4021) | -0.6154 | (-0.8710, -0.0974) | -0.7224 | (-0.9108, -0.2848) | graph_scatterplot |
| 3 | ULCh | 0.6154 | (0.0974, 0.8710) | 0.4615 | (-0.1200, 0.8072) | 0.6247 | (0.1125, 0.8747) | graph_scatterplot |
| 4 | TER-v0.7.25 | -0.8352 | (-0.9493, -0.5264) | -0.6923 | (-0.9000, -0.2285) | -0.9131 | (-0.9740, -0.7287) | graph_scatterplot |
| 5 | DP-Orp | 0.1898 | (-0.4034, 0.6707) | 0.1677 | (-0.4223, 0.6579) | 0.1158 | (-0.4649, 0.6268) | graph_scatterplot |
| 6 | NIST-v11b | 0.7967 | (0.4380, 0.9366) | 0.6154 | (0.0974, 0.8710) | 0.7209 | (0.2818, 0.9103) | graph_scatterplot |
| 7 | ATEC4 | 0.8022 | (0.4502, 0.9384) | 0.6410 | (0.1392, 0.8809) | 0.7611 | (0.3618, 0.9244) | graph_scatterplot |
| 8 | ATEC1 | 0.8022 | (0.4502, 0.9384) | 0.6410 | (0.1392, 0.8809) | 0.7463 | (0.3317, 0.9193) | graph_scatterplot |
| 9 | SNR | 0.6099 | (0.0887, 0.8689) | 0.4359 | (-0.1515, 0.7958) | 0.6176 | (0.1010, 0.8719) | graph_scatterplot |
| 10 | mBLEU | -0.2857 | (-0.7229, 0.3148) | -0.1538 | (-0.6498, 0.4339) | 0.4146 | (-0.1768, 0.7860) | graph_scatterplot |
| 11 | 4-GRR | 0.8407 | (0.5396, 0.9511) | 0.7179 | (0.2762, 0.9093) | 0.9140 | (0.7313, 0.9743) | graph_scatterplot |
| 12 | ATEC2 | 0.8132 | (0.4750, 0.9421) | 0.6667 | (0.1828, 0.8905) | 0.7594 | (0.3583, 0.9238) | graph_scatterplot |
| 13 | SEPIA1 | 0.7857 | (0.4139, 0.9329) | 0.5641 | (0.0190, 0.8507) | 0.7024 | (0.2470, 0.9037) | graph_scatterplot |
| 14 | ULCopt | 0.6154 | (0.0974, 0.8710) | 0.4615 | (-0.1200, 0.8072) | 0.6456 | (0.1469, 0.8826) | graph_scatterplot |
| 15 | EDPM | 0.8077 | (0.4625, 0.9402) | 0.6154 | (0.0974, 0.8710) | 0.8137 | (0.4763, 0.9423) | graph_scatterplot |
| 16 | mTER | -0.5659 | (-0.8514, -0.0217) | -0.4103 | (-0.7840, 0.1818) | -0.5065 | (-0.8268, 0.0617) | graph_scatterplot |
| 17 | BLEU-4 | 0.8022 | (0.4502, 0.9384) | 0.5897 | (0.0574, 0.8610) | 0.8150 | (0.4792, 0.9427) | graph_scatterplot |
| 18 | METEOR-v0.6 | 0.5824 | (0.0463, 0.8581) | 0.4359 | (-0.1515, 0.7958) | 0.6246 | (0.1122, 0.8746) | graph_scatterplot |
| 19 | BadgerLite | 0.3352 | (-0.2647, 0.7480) | 0.3077 | (-0.2930, 0.7342) | 0.4030 | (-0.1903, 0.7806) | graph_scatterplot |
| 20 | METEOR-ranking | 0.6154 | (0.0974, 0.8710) | 0.4615 | (-0.1200, 0.8072) | 0.6234 | (0.1103, 0.8741) | graph_scatterplot |
| 21 | LET | 0.7692 | (0.3788, 0.9272) | 0.5385 | (-0.0178, 0.8402) | 0.7421 | (0.3234, 0.9178) | graph_scatterplot |
| 22 | DP-Or | 0.6520 | (0.1576, 0.8850) | 0.5032 | (-0.0661, 0.8254) | 0.6612 | (0.1733, 0.8885) | graph_scatterplot |
| 23 | ATEC3 | 0.8077 | (0.4625, 0.9402) | 0.6410 | (0.1392, 0.8809) | 0.7667 | (0.3735, 0.9264) | graph_scatterplot |
| 24 | BLEU-v12 | 0.7912 | (0.4259, 0.9347) | 0.5641 | (0.0190, 0.8507) | 0.8216 | (0.4944, 0.9449) | graph_scatterplot |
| 25 | BEwT-E | 0.4835 | (-0.0920, 0.8169) | 0.3333 | (-0.2666, 0.7471) | 0.4277 | (-0.1613, 0.7920) | graph_scatterplot |
| 26 | DR-Or | 0.5604 | (0.0137, 0.8492) | 0.3846 | (-0.2111, 0.7720) | 0.6017 | (0.0759, 0.8657) | graph_scatterplot |
| 27 | BleuSP | 0.7363 | (0.3117, 0.9158) | 0.5128 | (-0.0532, 0.8294) | 0.6782 | (0.2032, 0.8948) | graph_scatterplot |
| 28 | SVM-Rank | 0.6209 | (0.1062, 0.8732) | 0.4872 | (-0.0872, 0.8185) | 0.5447 | (-0.0090, 0.8427) | graph_scatterplot |
| 29 | BLEU-1 | 0.6758 | (0.1989, 0.8939) | 0.4872 | (-0.0872, 0.8185) | 0.6647 | (0.1794, 0.8898) | graph_scatterplot |
| 30 | Bleu-sbp | 0.8022 | (0.4502, 0.9384) | 0.5897 | (0.0574, 0.8610) | 0.8112 | (0.4704, 0.9414) | graph_scatterplot |
| 31 | invWer | -0.8132 | (-0.9421, -0.4750) | -0.6410 | (-0.8809, -0.1392) | -0.8221 | (-0.9450, -0.4956) | graph_scatterplot |
| 32 | BLEU-v11b | 0.8022 | (0.4502, 0.9384) | 0.5897 | (0.0574, 0.8610) | 0.8350 | (0.5260, 0.9493) | graph_scatterplot |
| 33 | SR-Or | 0.6154 | (0.0974, 0.8710) | 0.4615 | (-0.1200, 0.8072) | 0.5978 | (0.0698, 0.8642) | graph_scatterplot |
| 34 | Badger | 0.3132 | (-0.2874, 0.7370) | 0.2308 | (-0.3669, 0.6936) | 0.3666 | (-0.2310, 0.7634) | graph_scatterplot |
| 35 | Meteor-v0.7 | 0.6154 | (0.0974, 0.8710) | 0.4615 | (-0.1200, 0.8072) | 0.6578 | (0.1675, 0.8872) | graph_scatterplot |
| 36 | MaxSim | 0.6813 | (0.2087, 0.8960) | 0.4872 | (-0.0872, 0.8185) | 0.6545 | (0.1619, 0.8860) | graph_scatterplot |
| 37 | TERp | -0.7473 | (-0.9196, -0.3336) | -0.5641 | (-0.8507, -0.0190) | -0.7414 | (-0.9176, -0.3220) | graph_scatterplot |
37 metrics (including 7 baseline metrics)
13 data points (total number of systems used)
|
