moses-smt/mosesdecoder
1
1
Fork 0
mirror of https://github.com/moses-smt/mosesdecoder.git synced 2024-09-20 23:58:15 +03:00
Code Issues Packages Projects Releases Wiki Activity
ddd2fdeb20
mosesdecoder/scripts/analysis
History
hieuhoang1972 ddd2fdeb20 Fix automount partition bug 
git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@1098 1f5c12ca-751b-0410-a591-d2e778427230
2006-12-29 00:59:59 +00:00
..
perllib minor, and moved stuff around 2006-08-08 23:38:45 +00:00
smtgui trying to fix caching 2006-08-17 12:31:52 +00:00
nontranslated_words.pl Just a short description added. 2006-09-21 12:23:42 +00:00
README updating docs 2006-08-16 16:37:11 +00:00
sentence-by-sentence.pl modified sentence-by-sentence to handle multiple outputs; 2006-08-16 14:49:10 +00:00
show-phrases-used.pl Fix automount partition bug 2006-12-29 00:59:59 +00:00

README 

Put any scripts useful for human analysis of MT output here.

sentence-by-sentence.pl [EVH]: show comparison of sentences in reference translation(s)/system output(s)/(truth) in colorful format
-- show 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`)

show-phrases-used.pl [EVH]: draw colorful diagram of which source phrases map to which target phrases
-- requires the Perl GD module, which in turn requires that gd be installed and in LD_LIBRARY_PATH
-- show average length of source phrases used for each sentence and overall
-- command-line options -r for reference and -s for source; lone filenames are taken to be system outputs