Just for anyone with same obstacles : it solved by binarize the phrase table as
follows
If phrase
table is large
~/mosesdecoder/bin/CreateOnDiskPt 1 1 4 100 2
~/Phd/April/nplm/-dir/model/phrase-table.gz phrase-table.folder
Change
moses.ini ::
[f
Hi all,
I trained BiLM with English-Arabic corpus , & it give better Blue score. But
when work with different bigger corpus I have this error !!
target_aligns[tpos].append(spos)IndexError: list index out of range
I have file .ngrams which stopped after small no of lines by this error ??? any
hel