Dear,
I am a student researching on SMT. Moses is an open powerful tool.
Recently I want to utilize word alignment in N-best output.
For example, translate chinese to english.
source sentence : 不过 ， 两 边 的 歧异 仍 存在 。
moses output: however , because the two sides still exist . ||| 0=0 1=1
5=2 4=3 2=4 3=5 6=6 7=7 8-8=8-8
The word alignment information above is outputted by Phrase-based model of
Moses. I tried to output word alignment information in Syntax-based model
such as Tree-to-Tree, hierarchical phrase-based but I failed. There is not
word alignment information in N-best file.
Can Syntax-based Model of Moses output word alignment information in
N-best file like Phrase-based Model ? and How to output word alignment
information?
Best Wishes!
htyang
2012.8.1
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
