Dear all,
I am doing the thesis on word alignment on English-Nepali corpus for SMT, but
in alignment I am so confused about how the word alignment can help on
Statistical Machine Translation.
Another thing is in Hidden Markov model for word alignment, what the
probability P(ai|Ai-1) is mean for? i.e. I cannot understand the effect of
previous alignment on next alignment. How the alignment probability depends on
previous alignment? And I can not realy understand the expanstion of the
Alignment probability in HMM, what the jump width is meant for? could you
please describe it in detail.
How I can get the actual algorithms of word alignment, please mention the sites
related to it and if you people have the pseudo code or Java code please
provide me.
And I am confused on the EM algorithm and Viterbi algorithm. please describe
about it also.
where can I get the information about the Moses alignment? How the alignment is
done in Moses.
please try to give me a detail information about it?
_________________________________________________________________
More than messages–check out the rest of the Windows Live™.
http://www.microsoft.com/windows/windowslive/
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
