hi zai,
in the pre-made models we released with version 1. of Moses
http://www.statmt.org/moses/RELEASE-1.0/models/fr-en/
The phrase 'vous ĂȘtes' appears to be aligned correctly. There are 330
translations of the phrase but the most probable translation is
vous ĂȘtes ||| you are ||| 0.219726 0.
This is a basic question as I am relatively new to Moses.
Can someone tell me why the alignment of texts is not picking up many (common)
words and phrases from the input? The decoder shows many UNKs that should not
be.
I am experimenting with a factored model using EMS and parallel corpora from