Difference between revisions of "Google Summer of Code/Midterm report 2011"
Jump to navigation
Jump to search
| Line 61: | Line 61: | ||
------------------------------------------------------- |
------------------------------------------------------- |
||
Number of words in reference: 456 |
Number of words in reference: 456 |
||
Number of words in test: |
Number of words in test: 453 |
||
Number of unknown words (marked with a star) in test: 2 |
Number of unknown words (marked with a star) in test: 2 |
||
Percentage of unknown words: 0.44 % |
Percentage of unknown words: 0.44 % |
||
| Line 67: | Line 67: | ||
Results when removing unknown-word marks (stars) |
Results when removing unknown-word marks (stars) |
||
------------------------------------------------------- |
------------------------------------------------------- |
||
Edit distance: |
Edit distance: 275 |
||
Word error rate (WER): |
Word error rate (WER): 60.71 % |
||
Number of position-independent word errors: |
Number of position-independent word errors: 207 |
||
Position-independent word error rate (PER): |
Position-independent word error rate (PER): 45.70 % |
||
Statistics about the translation of unknown words |
Statistics about the translation of unknown words |
||
| Line 76: | Line 76: | ||
Number of unknown words which were free rides: 0 |
Number of unknown words which were free rides: 0 |
||
Percentage of unknown words that were free rides: 0.00 % |
Percentage of unknown words that were free rides: 0.00 % |
||
</pre> |
</pre> |
||
Revision as of 16:20, 14 July 2011
Language pairs
For language pairs, we have two tasks, for some pairs the task was to translate a news article without any diagnostics and evaluate the output. For the other pairs, the task was to create morphological analysers with 80% coverage.
Turkish → Azerbaijani
- See also: apertium-tr-az/dev/midterm
Statistics about input files ------------------------------------------------------- Number of words in reference: 356 Number of words in test: 364 Number of unknown words (marked with a star) in test: 4 Percentage of unknown words: 1.10 % Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 52 Word error rate (WER): 14.29 % Number of position-independent word errors: 50 Position-independent word error rate (PER): 13.74 % Statistics about the translation of unknown words ------------------------------------------------------- Number of unknown words which were free rides: 1 Percentage of unknown words that were free rides: 25.00 %
Turkish → Kyrgyz
- See also: apertium-tr-ky/dev/midterm
Statistics about input files ------------------------------------------------------- Number of words in reference: 380 Number of words in test: 371 Number of unknown words (marked with a star) in test: 5 Percentage of unknown words: 1.35 % Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 209 Word error rate (WER): 56.33 % Number of position-independent word errors: 197 Position-independent word error rate (PER): 53.10 % Statistics about the translation of unknown words ------------------------------------------------------- Number of unknown words which were free rides: 0 Percentage of unknown words that were free rides: 0.00 %
Serbo-Croatian → Macedonian
Statistics about input files ------------------------------------------------------- Number of words in reference: 456 Number of words in test: 453 Number of unknown words (marked with a star) in test: 2 Percentage of unknown words: 0.44 % Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 275 Word error rate (WER): 60.71 % Number of position-independent word errors: 207 Position-independent word error rate (PER): 45.70 % Statistics about the translation of unknown words ------------------------------------------------------- Number of unknown words which were free rides: 0 Percentage of unknown words that were free rides: 0.00 %
Slovenian → Spanish
Statistics about input files ------------------------------------------------------- Number of words in reference: 487 Number of words in test: 456 Number of unknown words (marked with a star) in test: 36 Percentage of unknown words: 7.89 % Results when removing unknown-word marks (stars) ------------------------------------------------------- Edit distance: 425 Word error rate (WER): 93.20 % Number of position-independent word errors: 375 Position-independent word error rate (PER): 82.24 % Statistics about the translation of unknown words ------------------------------------------------------- Number of unknown words which were free rides: 11 Percentage of unknown words that were free rides: 30.56 %
