diff options
author | bojar <bojar@1f5c12ca-751b-0410-a591-d2e778427230> | 2006-09-21 16:23:42 +0400 |
---|---|---|
committer | bojar <bojar@1f5c12ca-751b-0410-a591-d2e778427230> | 2006-09-21 16:23:42 +0400 |
commit | c6c02a83c6a965d3d314524da6ec71ce79377f70 (patch) | |
tree | 81c74d14495291294ed213acbe4544fc1e476e1f /scripts/analysis | |
parent | 735d2f53490bb184f0cb8419f9abb6ccef132f15 (diff) |
Just a short description added.
git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@823 1f5c12ca-751b-0410-a591-d2e778427230
Diffstat (limited to 'scripts/analysis')
-rwxr-xr-x | scripts/analysis/nontranslated_words.pl | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/scripts/analysis/nontranslated_words.pl b/scripts/analysis/nontranslated_words.pl index 687eaae20..42fff57ee 100755 --- a/scripts/analysis/nontranslated_words.pl +++ b/scripts/analysis/nontranslated_words.pl @@ -1,5 +1,11 @@ #!/usr/bin/perl +# Reads a source and hypothesis file and counts equal tokens. Some of these +# are punctuation, some are numbers, but most of the remaining are simply +# unknown words that the decoder just copied. This script tells you how often +# this happens. # +# Ondrej Bojar + use strict; use warnings; |