Current Results
The live analysis fits a source-to-target length baseline and then looks for source and target terms associated with unexpectedly long or short translations. Positive residuals mean the translation spends more words than expected after controlling for source length.
Segments3170
Works1
Metrictokens
Baselinelog
R squared0.862
Residual SD0.100
Source features2000
Target features2000
Source Length vs Target Length
Source Terms Predicting Residuals
| Feature | Coefficient | Segments | Mean residual with | Mean residual without |
|---|---|---|---|---|
| ἑλένης | 0.0463 | 18 | 0.091 | -0.001 |
| τὸ ἱερόν | -0.0415 | 38 | -0.026 | 0.000 |
| πελοποννησίων | 0.0393 | 31 | 0.057 | -0.001 |
| καθέστηκεν | 0.0379 | 40 | 0.030 | -0.000 |
| ἄλλοι | -0.0374 | 77 | -0.047 | 0.001 |
| τοῦ μὲν | 0.0368 | 18 | 0.033 | -0.000 |
| οὐκ ἂν | 0.0356 | 22 | 0.055 | -0.000 |
| unknown | -0.0346 | 30 | -0.030 | 0.000 |
| θεὸς | 0.0335 | 57 | 0.030 | -0.001 |
| παλαιοῦ | 0.0332 | 30 | 0.053 | -0.001 |
| μεσσηνίοις | 0.0331 | 59 | 0.039 | -0.001 |
| ἡρῷον | 0.0331 | 26 | 0.084 | -0.001 |
| καὶ ταῖς | -0.0328 | 18 | -0.057 | 0.000 |
| ἱερόν | 0.0322 | 169 | 0.027 | -0.002 |
| τῇ πόλει | -0.0318 | 76 | -0.010 | 0.000 |
| ἐκ παλαιοῦ | 0.0318 | 29 | 0.053 | -0.000 |
| νομίζοντες | 0.0317 | 22 | 0.028 | -0.000 |
| χρημάτων | 0.0317 | 45 | 0.027 | -0.000 |
| δρόμον | 0.0315 | 23 | 0.040 | -0.000 |
| δὲ ἢ | -0.0315 | 28 | -0.031 | 0.000 |
| πολλά | -0.0315 | 21 | -0.035 | 0.000 |
| αὐτοῖς καὶ | 0.0314 | 18 | 0.020 | -0.000 |
| τὸ ἀπὸ | -0.0309 | 23 | -0.069 | 0.001 |
| ἀνδρῶν | 0.0308 | 67 | 0.022 | -0.000 |
| ἐντεῦθεν | 0.0306 | 50 | 0.036 | -0.001 |
Target Terms Predicting Residuals
| Feature | Coefficient | Segments | Mean residual with | Mean residual without |
|---|---|---|---|---|
| make | 0.0350 | 53 | 0.045 | -0.001 |
| dedicated to | 0.0342 | 166 | 0.042 | -0.002 |
| even to | 0.0334 | 51 | 0.053 | -0.001 |
| because he | 0.0325 | 37 | 0.063 | -0.001 |
| rivers | -0.0321 | 28 | -0.073 | 0.001 |
| a great | 0.0312 | 30 | 0.039 | -0.000 |
| the sons | 0.0307 | 104 | 0.006 | -0.000 |
| who won | 0.0305 | 30 | 0.066 | -0.001 |
| year of | 0.0303 | 25 | 0.024 | -0.000 |
| orchomenus | -0.0296 | 32 | -0.073 | 0.001 |
| who composed | -0.0295 | 26 | -0.032 | 0.000 |
| that a | 0.0293 | 38 | 0.053 | -0.001 |
| proclaimed | -0.0292 | 31 | -0.009 | 0.000 |
| armor | 0.0289 | 27 | 0.027 | -0.000 |
| a temple | 0.0289 | 208 | 0.039 | -0.003 |
| poetry | -0.0287 | 42 | -0.031 | 0.000 |
| use | 0.0287 | 25 | 0.055 | -0.000 |
| here the | -0.0284 | 36 | -0.024 | 0.000 |
| road from | -0.0278 | 30 | -0.029 | 0.000 |
| cavalry | -0.0277 | 35 | -0.049 | 0.001 |
| are said | -0.0276 | 35 | -0.014 | 0.000 |
| me to | 0.0276 | 25 | 0.043 | -0.000 |
| established the | 0.0272 | 35 | 0.052 | -0.001 |
| shall | 0.0272 | 76 | 0.041 | -0.001 |
| fought against | 0.0270 | 30 | 0.023 | -0.000 |
Downloads
metrics.json segments.csv source_predictors.csv target_predictors.csv