shouldn't the Belu score be more in the 50's for a test set close to the
corpus ?
I meant by real text that I have a corpus of translations (fr to eng)
made by translators, typically the kind of text I would like to test
with Moses.
so my question is : should I use these texts to 1) train
here is what I got
make sense ?
MT evaluation scorer began on 2015 Jul 20 at 23:27:39
command line: /home/moses/mosesdecoder/scripts/generic/mteval-v13a.pl -c
-c -s /home/moses/working/data/dev/newstest2011-src.fr.sgm -r
/home/moses/working/data/dev/newstest2011-ref.en.sgm -t
Dears,
I have a BLEU result with 77.67
I used files with 5000 lines to test with, could this result be a fake one?
as the quality does not fit this result as I think
Best Regards
Ihab Ramadan| Senior Developer| http://www.saudisoft.com/ Saudisoft -
Egypt | Tel +2 02 330 320 37 Ext- 0 |
5,000 lines is way too many. You probably only need 2000-3000.
Here are my questions:
1. How many duplicate segments (source target sentence pairs) are
replicated/repeated in your training corpus?
2. Are your test segments similar to/same/different from your tuning set?
3. How did you