barebone support for quality estimation in experiment.perl

3 files changed, 69 insertions, 3 deletions

diff --git a/scripts/ems/support/create-xml.perl b/scripts/ems/support/create-xml.perl
new file mode 100755
index 000000000..610c2ccf8
--- /dev/null
+++ b/scripts/ems/support/create-xml.perl
@@ -0,0 +1,42 @@
+#!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
+
+use warnings;
+use strict;
+
+my ($type) = @ARGV;
+if ($type =~ /^s/i) {
+	print "<srcset setid=\"test\" srclang=\"any\">\n";
+	print "<doc docid=\"doc\">\n";
+}
+elsif ($type =~ /^t/i) {
+	print "<tstset setid=\"test\" tgtlang=\"any\" srclang=\"any\">\n";
+	print "<doc sysid=\"moses\" docid=\"doc\">\n";
+}
+elsif ($type =~ /^r/i) {
+	print "<refset setid=\"test\" tgtlang=\"any\" srclang=\"any\">\n";
+	print "<doc sysid=\"ref\" docid=\"doc\">\n";
+}
+else {
+	die("ERROR: specify source / target / ref");
+}
+
+my $i = 0;
+while(<STDIN>) {
+  chomp;
+  print "<seg id=\"".(++$i)."\">$_</seg>\n";
+}
+
+print "</doc>\n";
+
+if ($type =~ /^s/i) {
+	print "</srcset>\n";
+}
+elsif ($type =~ /^t/i) {
+	print "</tstset>\n";	
+}
+elsif ($type =~ /^r/i) {
+	print "</refset>\n";
+}
diff --git a/scripts/ems/support/remove-segmentation-markup.perl b/scripts/ems/support/remove-segmentation-markup.perl
index 3b02bceaf..1e5820dd5 100755
--- a/scripts/ems/support/remove-segmentation-markup.perl
+++ b/scripts/ems/support/remove-segmentation-markup.perl
@@ -9,7 +9,16 @@ use strict;
 $|++;
 
 while(<STDIN>) {
-  s/ \|\d+\-\d+\| / /g;
-  s/ \|\d+\-\d+\|$//;
-  print $_;
+  chop;
+  s/\|[^\|]+\|//g;
+  s/\s+/ /g;
+  s/^ //;
+  s/ $//;
+  print $_."\n";
 }
+
+#while(<STDIN>) {
+#  s/ \|\d+\-\d+\| / /g;
+#  s/ \|\d+\-\d+\|$//;
+#  print $_;
+#}
diff --git a/scripts/ems/support/ter.perl b/scripts/ems/support/ter.perl
new file mode 100644
index 000000000..1bae6f146
--- /dev/null
+++ b/scripts/ems/support/ter.perl
@@ -0,0 +1,15 @@
+#!/usr/bin/env perl
+#
+# This file is part of moses.  Its use is licensed under the GNU Lesser General
+# Public License version 2.1 or, at your option, any later version.
+
+use strict;
+use FindBin qw($RealBin);
+
+my ($jar, $hyp,$ref,$tmp) = @ARGV;
+`mkdir -p $tmp`;
+`$RealBin/create-xml.perl test < $hyp > $tmp/hyp`;
+`$RealBin/create-xml.perl ref  < $ref > $tmp/ref`;
+`java -jar $jar -h $tmp/hyp -r $tmp/ref -o ter -n $tmp/out`;
+print `cat $tmp/out.ter`;
+