Hi john
I'm afraid the word alignment tools like Giza++ aren't really designed to
be run against paragraph length input. Probably one reason why you're
getting bad alignments.
I don't know is tweaking the parameters would make it any better, or using
any other word alignment tool
On Wed, Jul 8,
Hi,
I'm using a 7162 line paragraph-aligned corpus. Unfortunately the
translation within the paragraph sometimes don't have the sentences
aligned, i.e. in one language the sentence could be one long sentence, and
in another language the sentence could have clauses broken up into multiple