Commit
•
9d43877
1
Parent(s):
3c7b25f
Update README.md
Browse files
README.md
CHANGED
|
@@ -215,7 +215,7 @@ sentences selected from the 3,000 sentence test set.
|
|
| 215 |
|
| 216 |
## Selected Language Evaluation Reports
|
| 217 |
For now, metrics for a few selected languages are shown below.
|
| 218 |
-
Given the amount of work required to collect pretty metrics in 47 languages, I'll add more eventually.
|
| 219 |
|
| 220 |
Expand any of the following tabs to see metrics for that language.
|
| 221 |
|
|
@@ -338,3 +338,125 @@ seg test report:
|
|
| 338 |
```
|
| 339 |
|
| 340 |
</details>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 215 |
|
| 216 |
## Selected Language Evaluation Reports
|
| 217 |
For now, metrics for a few selected languages are shown below.
|
| 218 |
+
Given the amount of work required to collect and pretty-print metrics in 47 languages, I'll add more eventually.
|
| 219 |
|
| 220 |
Expand any of the following tabs to see metrics for that language.
|
| 221 |
|
|
|
|
| 338 |
```
|
| 339 |
|
| 340 |
</details>
|
| 341 |
+
|
| 342 |
+
|
| 343 |
+
<details>
|
| 344 |
+
<summary>Amharic</summary>
|
| 345 |
+
|
| 346 |
+
```text
|
| 347 |
+
punct_post test report:
|
| 348 |
+
label precision recall f1 support
|
| 349 |
+
<NULL> (label_id: 0) 99.81 99.40 99.60 729695
|
| 350 |
+
<ACRONYM> (label_id: 1) 0.00 0.00 0.00 0
|
| 351 |
+
. (label_id: 2) 0.00 0.00 0.00 0
|
| 352 |
+
, (label_id: 3) 0.00 0.00 0.00 0
|
| 353 |
+
? (label_id: 4) 0.00 0.00 0.00 0
|
| 354 |
+
？ (label_id: 5) 0.00 0.00 0.00 0
|
| 355 |
+
， (label_id: 6) 0.00 0.00 0.00 0
|
| 356 |
+
。 (label_id: 7) 0.00 0.00 0.00 0
|
| 357 |
+
、 (label_id: 8) 0.00 0.00 0.00 0
|
| 358 |
+
・ (label_id: 9) 0.00 0.00 0.00 0
|
| 359 |
+
। (label_id: 10) 0.00 0.00 0.00 0
|
| 360 |
+
؟ (label_id: 11) 0.00 0.00 0.00 0
|
| 361 |
+
، (label_id: 12) 0.00 0.00 0.00 0
|
| 362 |
+
; (label_id: 13) 0.00 0.00 0.00 0
|
| 363 |
+
። (label_id: 14) 91.44 97.78 94.50 25288
|
| 364 |
+
፣ (label_id: 15) 66.93 80.45 73.07 5774
|
| 365 |
+
፧ (label_id: 16) 72.14 77.01 74.49 1170
|
| 366 |
+
-------------------
|
| 367 |
+
micro avg 99.17 99.17 99.17 761927
|
| 368 |
+
macro avg 82.58 88.66 85.42 761927
|
| 369 |
+
weighted avg 99.24 99.17 99.19 761927
|
| 370 |
+
```
|
| 371 |
+
|
| 372 |
+
```text
|
| 373 |
+
cap test report:
|
| 374 |
+
label precision recall f1 support
|
| 375 |
+
LOWER (label_id: 0) 98.50 97.22 97.86 1150
|
| 376 |
+
UPPER (label_id: 1) 56.16 70.69 62.60 58
|
| 377 |
+
-------------------
|
| 378 |
+
micro avg 95.94 95.94 95.94 1208
|
| 379 |
+
macro avg 77.33 83.95 80.23 1208
|
| 380 |
+
weighted avg 96.47 95.94 96.16 1208
|
| 381 |
+
```
|
| 382 |
+
|
| 383 |
+
```text
|
| 384 |
+
seg test report:
|
| 385 |
+
label precision recall f1 support
|
| 386 |
+
NOSTOP (label_id: 0) 99.97 99.91 99.94 743103
|
| 387 |
+
FULLSTOP (label_id: 1) 97.16 99.04 98.09 21824
|
| 388 |
+
-------------------
|
| 389 |
+
micro avg 99.89 99.89 99.89 764927
|
| 390 |
+
macro avg 98.57 99.48 99.02 764927
|
| 391 |
+
weighted avg 99.89 99.89 99.89 764927
|
| 392 |
+
```
|
| 393 |
+
|
| 394 |
+
</details>
|
| 395 |
+
|
| 396 |
+
|
| 397 |
+
<details>
|
| 398 |
+
<summary>Chinese</summary>
|
| 399 |
+
|
| 400 |
+
```text
|
| 401 |
+
punct_post test report:
|
| 402 |
+
label precision recall f1 support
|
| 403 |
+
<NULL> (label_id: 0) 99.47 97.46 98.45 414383
|
| 404 |
+
<ACRONYM> (label_id: 1) 0.00 0.00 0.00 0
|
| 405 |
+
. (label_id: 2) 0.00 0.00 0.00 0
|
| 406 |
+
, (label_id: 3) 0.00 0.00 0.00 0
|
| 407 |
+
? (label_id: 4) 0.00 0.00 0.00 0
|
| 408 |
+
？ (label_id: 5) 81.41 85.80 83.55 1444
|
| 409 |
+
， (label_id: 6) 74.93 92.79 82.91 34094
|
| 410 |
+
。 (label_id: 7) 96.35 96.86 96.60 30668
|
| 411 |
+
、 (label_id: 8) 0.00 0.00 0.00 0
|
| 412 |
+
・ (label_id: 9) 0.00 0.00 0.00 0
|
| 413 |
+
। (label_id: 10) 0.00 0.00 0.00 0
|
| 414 |
+
؟ (label_id: 11) 0.00 0.00 0.00 0
|
| 415 |
+
، (label_id: 12) 0.00 0.00 0.00 0
|
| 416 |
+
; (label_id: 13) 0.00 0.00 0.00 0
|
| 417 |
+
። (label_id: 14) 0.00 0.00 0.00 0
|
| 418 |
+
፣ (label_id: 15) 0.00 0.00 0.00 0
|
| 419 |
+
፧ (label_id: 16) 0.00 0.00 0.00 0
|
| 420 |
+
-------------------
|
| 421 |
+
micro avg 97.05 97.05 97.05 480589
|
| 422 |
+
macro avg 88.04 93.23 90.38 480589
|
| 423 |
+
weighted avg 97.47 97.05 97.19 480589
|
| 424 |
+
```
|
| 425 |
+
|
| 426 |
+
```text
|
| 427 |
+
cap test report:
|
| 428 |
+
label precision recall f1 support
|
| 429 |
+
LOWER (label_id: 0) 94.82 93.97 94.39 2786
|
| 430 |
+
UPPER (label_id: 1) 79.23 81.76 80.48 784
|
| 431 |
+
-------------------
|
| 432 |
+
micro avg 91.29 91.29 91.29 3570
|
| 433 |
+
macro avg 87.03 87.87 87.44 3570
|
| 434 |
+
weighted avg 91.40 91.29 91.34 3570
|
| 435 |
+
```
|
| 436 |
+
|
| 437 |
+
```text
|
| 438 |
+
seg test report:
|
| 439 |
+
label precision recall f1 support
|
| 440 |
+
NOSTOP (label_id: 0) 99.99 99.98 99.98 450589
|
| 441 |
+
FULLSTOP (label_id: 1) 99.75 99.81 99.78 33000
|
| 442 |
+
-------------------
|
| 443 |
+
micro avg 99.97 99.97 99.97 483589
|
| 444 |
+
macro avg 99.87 99.89 99.88 483589
|
| 445 |
+
weighted avg 99.97 99.97 99.97 483589
|
| 446 |
+
```
|
| 447 |
+
|
| 448 |
+
</details>
|
| 449 |
+
|
| 450 |
+
|
| 451 |
+
<details>
|
| 452 |
+
<summary>Japanese</summary>
|
| 453 |
+
|
| 454 |
+
|
| 455 |
+
</details>
|
| 456 |
+
|
| 457 |
+
|
| 458 |
+
<details>
|
| 459 |
+
<summary>Hindi</summary>
|
| 460 |
+
|
| 461 |
+
|
| 462 |
+
</details>
|