you might want to take a look at our old paper
http://homepages.inf.ed.ac.uk/pkoehn/publications/emnlp2007-factored.pdf
On 06/02/2017 18:31, Lakshya wrote:
Dear All,
Could anybody please help me to get details about the following doubts ?
1. The impact of OOV counts as the number of factors increases in
Factor-based-SMT model for morphologically rich languages?
2. How good is the improvement of factor based models with MERT
tuning ? Did anybody experimented ?
Expecting a reply soon,
Regards
Lakshya
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
--
Hieu Hoang
http://moses-smt.org/
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
