blob: 6e28bc9e0e085d4fc7a99bb095a541c1a9074a9a (
plain)
1
2
3
4
5
6
|
Put any scripts useful for human analysis of MT output here.
[EVH]
sentence-by-sentence.pl: show comparison of sentences in reference translation(s)/system otuput/(truth) in colorful format
-- shows all sentences given, with non-matching words in the system output marked, BLEU scores given by sentence, and matching n-grams shown in a table
-- requires all input files be utf8-encoded (you can convert a file with `cat FILE | perl -n -e 'binmode(STDOUT, ":utf8"); print;' > FILE.utf8`)
|