Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/moses-smt/mosesdecoder.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorbhaddow <barry.haddow@gmail.com>2011-12-16 21:00:13 +0400
committerbhaddow <barry.haddow@gmail.com>2011-12-16 21:00:13 +0400
commitb0e0546dd901983f2cda726656e3855f5da298c5 (patch)
treed27ac7770db8a89f68d8c3d5d0e87902f1dba5c1 /scripts/generic
parent63f2b4b07adde3259fc3e9a25ac3fc6ba341602b (diff)
Add option to lowercase input
Diffstat (limited to 'scripts/generic')
-rwxr-xr-xscripts/generic/multi-bleu.perl10
1 files changed, 9 insertions, 1 deletions
diff --git a/scripts/generic/multi-bleu.perl b/scripts/generic/multi-bleu.perl
index a24cd2cc7..06f01acff 100755
--- a/scripts/generic/multi-bleu.perl
+++ b/scripts/generic/multi-bleu.perl
@@ -3,9 +3,15 @@
# $Id$
use strict;
+my $lowercase = 0;
+if ($ARGV[0] eq "-lc") {
+ $lowercase = 1;
+ shift;
+}
+
my $stem = $ARGV[0];
if (!defined $stem) {
- print STDERR "usage: multi-bleu.pl reference < hypothesis\n";
+ print STDERR "usage: multi-bleu.pl [-lc] reference < hypothesis\n";
print STDERR "Reads the references from reference or reference0, reference1, ...\n";
exit(1);
}
@@ -35,12 +41,14 @@ my(@CORRECT,@TOTAL,$length_translation,$length_reference);
my $s=0;
while(<STDIN>) {
chop;
+ $_ = lc if $lowercase;
my @WORD = split;
my %REF_NGRAM = ();
my $length_translation_this_sentence = scalar(@WORD);
my ($closest_diff,$closest_length) = (9999,9999);
foreach my $reference (@{$REF[$s]}) {
# print "$s $_ <=> $reference\n";
+ $reference = lc($reference) if $lowercase;
my @WORD = split(/ /,$reference);
my $length = scalar(@WORD);
my $diff = abs($length_translation_this_sentence-$length);