add regression test binary models with lex reordering. Fix other regression tests - changed to account for new LM prob from IRST or use KenLM

git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@4367 1f5c12ca-751b-0410-a591-d2e778427230

5 files changed, 110 insertions, 0 deletions

diff --git a/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stderr.pl b/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stderr.pl
new file mode 100755
index 000000000..2f6e17607
--- /dev/null
+++ b/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stderr.pl
@@ -0,0 +1,22 @@
+#!/usr/bin/perl
+
+BEGIN { use Cwd qw/ abs_path /; use File::Basename; $script_dir = dirname(abs_path($0)); push @INC, "$script_dir/../perllib"; }
+use RegTestUtils;
+
+$x=0;
+while (<>) {
+  chomp;
+
+  if (/^Finished loading LanguageModels/) {
+    my $time = RegTestUtils::readTime($_);
+    print "LMLOAD_TIME ~ $time\n";
+  }
+  if (/^Finished loading phrase tables/) {
+    my $time = RegTestUtils::readTime($_);
+    print "PTLOAD_TIME ~ $time\n";
+  }
+  next unless /^BEST TRANSLATION:/;
+  my $pscore = RegTestUtils::readHypoScore($_);
+  $x++;
+  print "SCORE_$x = $pscore\n";
+}
diff --git a/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stdout.pl b/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stdout.pl
new file mode 100755
index 000000000..476ddf6e9
--- /dev/null
+++ b/regression-testing/tests/phrase.lexicalized-reordering-bin/filter-stdout.pl
@@ -0,0 +1,7 @@
+#!/usr/bin/perl
+$x=0;
+while (<>) {
+  chomp;
+  $x++;
+  print "TRANSLATION_$x=$_\n";
+}
diff --git a/regression-testing/tests/phrase.lexicalized-reordering-bin/moses.ini b/regression-testing/tests/phrase.lexicalized-reordering-bin/moses.ini
new file mode 100644
index 000000000..fb536f9a9
--- /dev/null
+++ b/regression-testing/tests/phrase.lexicalized-reordering-bin/moses.ini
@@ -0,0 +1,63 @@
+#########################
+### MOSES CONFIG FILE ###
+#########################
+
+# input factors
+[input-factors]
+0
+
+# mapping steps
+[mapping]
+T 0
+
+# translation tables: source-factors, target-factors, number of scores, file 
+[ttable-file]
+1 0 0 5 ${MODEL_PATH}/lexicalized-reordering-bin/phrase-table
+
+# no generation models, no generation-file section
+
+# language models: type(srilm/irstlm), factors, order, file
+[lmodel-file]
+0 0 5 ${MODEL_PATH}/lexicalized-reordering/europarl.lm
+
+
+# limit on how many phrase translations e for each phrase f are loaded
+# 0 = all elements loaded
+[ttable-limit]
+20
+0
+# distortion (reordering) files
+[distortion-file]
+0-0 msd-bidirectional-fe 6 ${MODEL_PATH}/lexicalized-reordering-bin/reordering-table.msd-bidirectional-fe
+
+# distortion (reordering) weight
+[weight-d]
+0.5
+0.3
+0.3
+0.3
+0.3
+0.3
+0.3
+
+# language model weights
+[weight-l]
+0.5000
+
+
+# translation model weights
+[weight-t]
+0.2
+0.2
+0.2
+0.2
+0.2
+
+# no generation models, no weight-generation section
+
+# word penalty
+[weight-w]
+-1
+
+[distortion-limit]
+6
diff --git a/regression-testing/tests/phrase.lexicalized-reordering-bin/to-translate.txt b/regression-testing/tests/phrase.lexicalized-reordering-bin/to-translate.txt
new file mode 100644
index 000000000..d336d82f3
--- /dev/null
+++ b/regression-testing/tests/phrase.lexicalized-reordering-bin/to-translate.txt
@@ -0,0 +1,5 @@
+monsieur le président , ce que nous devrons toutefois également faire à biarritz , c' est regarder un peu plus loin .
+les élus que nous sommes avons au moins autant le devoir de l' encourager à progresser , en dépit de l' adversité , que de relayer les messages que nous recevons de l' opinion publique dans chacun de nos pays .
+au regard des événements de ces derniers temps , la question du prix de l' essence me semble elle aussi particulièrement remarquable .
+à l' heure actuelle , le conseil est en train d' examiner l' inclusion de tels mécanismes dans l' article 7 .
+deuxièmement , dans la transparence pour les citoyens , qui connaissent à présent les droits dont ils disposent vis-à-vis de ceux qui appliquent et élaborent le droit européen , et pour ceux qui , justement , appliquent et élaborent ce droit européen .
diff --git a/regression-testing/tests/phrase.lexicalized-reordering-bin/truth/results.txt b/regression-testing/tests/phrase.lexicalized-reordering-bin/truth/results.txt
new file mode 100644
index 000000000..9c56d1e73
--- /dev/null
+++ b/regression-testing/tests/phrase.lexicalized-reordering-bin/truth/results.txt
@@ -0,0 +1,13 @@
+TRANSLATION_1=mr president , what we devrons but also to to biarritz , this is regarder a little more loin . 
+TRANSLATION_2=the élus that we are have the with difference the us of the encourager to progresser , in dépit of the adversité , that of relayer the messages that we recevons of the opinion all in each of our countries . 
+TRANSLATION_3=the prerequisites for the événements of these derniers time , the issue of the sufficiently of the essence to it also in remarquable . 
+TRANSLATION_4=in the , the council , it is train of examiner the inclusion of such mécanismes in article 7 . 
+TRANSLATION_5=secondly , in the transparency for the citizens , which are now the droits which they disposent vis-à-vis of those appliquent and élaborent the european law and , to those , precisely appliquent and élaborent this european law . 
+LMLOAD_TIME ~ 8.00
+PTLOAD_TIME ~ 9.00
+SCORE_1 = -621.292
+SCORE_2 = -1402.951
+SCORE_3 = -636.300
+SCORE_4 = -631.966
+SCORE_5 = -1110.523
+TOTAL_WALLTIME ~ 16