>
>
> Dear Sir/Madam
>
> Please Please Please help me. I am still confused that file generated with
> ".A3.final" extension by MOSES contains information like given below:
>
> # Sentence pair (3) source length 10 target length 9
> *alignment score :1.48814e-16*
> this is a famous abode of Lord Shiva .
>
NULL ({ }) गंगा ({ 3 }) किनारे ({ }) यह ({ 1 }) भगवान ({ 7 }) शंकर ({ 8 })
की ({ 6 }) प्रसिद्ध ({ 4 }) पुरी ({ 5 }) है ({ 2 }) । ({ 9 })
>
> I want to know what is this alignment score. Some people says that it is
> viterbi alignment score generated by HMM. Some people says that it is
> alignment score generated by IBM Model 4 and give reference of ?The
> Mathematics of Statistical Machine Translation: Parameter Estimation?.
> Honestly, I read that document many times and it is really hard to
> understand for me to know exactly "alignment score". Is this "relative
> distortion a(i|j, m,l)"?
> I want to know that if I need to describe this alignment score in one line
> then what should I write?
> Please help me.
>
> Thanks and regards
> Jyoti Srivastava
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
