Difference between revisions of "Meta-evaluation"
Jump to navigation
Jump to search
Firespeaker (talk | contribs) m |
Firespeaker (talk | contribs) m |
||
| Line 5: | Line 5: | ||
** Monolingual naïve coverage |
** Monolingual naïve coverage |
||
** Trimmed naïve coverage (i.e., using a trimmed dictionary) |
** Trimmed naïve coverage (i.e., using a trimmed dictionary) |
||
* Accuracy of tagging |
* Accuracy of tagging |
||
** Precision/Recall/F-score |
** Precision/Recall/F-score |
||
* Accuracy of translation |
* Accuracy of translation |
||
Revision as of 22:01, 30 May 2019
Apertium language modules and translation pairs are subject to the following types of evaluation:
- Naïve coverage
- Monolingual naïve coverage
- Trimmed naïve coverage (i.e., using a trimmed dictionary)
- Accuracy of tagging
- Precision/Recall/F-score
- Accuracy of translation
- WER/PER/BLEU
- Clenliness of translation output
- Testvoc
