Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Test file: 'paper/evaluation/kaz-tat.19042013.txt'
- Reference file 'paper/evaluation/kaz-tat.postedit.txt'
- Statistics about input files
- -------------------------------------------------------
- Number of words in reference: 2934
- Number of words in test: 2937
- Number of unknown words (marked with a star) in test: 43
- Percentage of unknown words: 1.46 %
- Results when removing unknown-word marks (stars)
- -------------------------------------------------------
- Edit distance: 1033
- Word error rate (WER): 35.21 %
- Number of position-independent correct words: 1996
- Position-independent word error rate (PER): 32.07 %
- Results when unknown-word marks (stars) are not removed
- -------------------------------------------------------
- Edit distance: 1076
- Word Error Rate (WER): 36.67 %
- Number of position-independent correct words: 1953
- Position-independent word error rate (PER): 33.54 %
- Statistics about the translation of unknown words
- -------------------------------------------------------
- Number of unknown words which were free rides: 43
- Percentage of unknown words that were free rides: 100.00 %
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement