diff options
author | phikoehn <pkoehn@inf.ed.ac.uk> | 2013-01-14 23:23:02 +0400 |
---|---|---|
committer | phikoehn <pkoehn@inf.ed.ac.uk> | 2013-01-14 23:23:02 +0400 |
commit | d5cf38cab2c64a7bb756e2a40b5a768e3a687249 (patch) | |
tree | c7bd1d83149359fdd27fdb8814bc81d0f024944c /scripts/ems | |
parent | 344b1503728364d164d2d9420f89726e7cb0c4a0 (diff) | |
parent | c9687e3b50d64174f091808fd2d6e04c7b17a406 (diff) |
Merge branch 'master' of git://github.com/moses-smt/mosesdecoder
Diffstat (limited to 'scripts/ems')
-rw-r--r-- | scripts/ems/experiment.meta | 6 | ||||
-rwxr-xr-x | scripts/ems/support/split-sentences.perl | 8 |
2 files changed, 7 insertions, 7 deletions
diff --git a/scripts/ems/experiment.meta b/scripts/ems/experiment.meta index 210fddb93..52596227c 100644 --- a/scripts/ems/experiment.meta +++ b/scripts/ems/experiment.meta @@ -401,21 +401,21 @@ mml-filter-before-wa prepare-data in: corpus-mml-prefilter=OR=corpus out: prepared-data - rerun-on-change: alignment-factors training-options script baseline-alignment-model + rerun-on-change: alignment-factors training-options script baseline-alignment-model external-bin-dr ignore-if: use-berkeley default-name: prepared run-giza in: prepared-data out: giza-alignment ignore-if: use-berkeley - rerun-on-change: giza-settings training-options script baseline-alignment-model + rerun-on-change: giza-settings training-options script baseline-alignment-model external-bin-dir default-name: giza error: not found not-error: 0 not found run-giza-inverse in: prepared-data out: giza-alignment-inverse - rerun-on-change: giza-settings training-options script baseline-alignment-model + rerun-on-change: giza-settings training-options script baseline-alignment-model external-bin-dir ignore-if: use-berkeley default-name: giza-inverse error: not found diff --git a/scripts/ems/support/split-sentences.perl b/scripts/ems/support/split-sentences.perl index b366d3d7e..d73e58742 100755 --- a/scripts/ems/support/split-sentences.perl +++ b/scripts/ems/support/split-sentences.perl @@ -84,16 +84,16 @@ sub do_it_for { } sub preprocess { + #this is one paragraph + my($text) = @_; + # clean up spaces at head and tail of each line as well as any double-spacing $text =~ s/ +/ /g; $text =~ s/\n /\n/g; $text =~ s/ \n/\n/g; $text =~ s/^ //g; $text =~ s/ $//g; - - #this is one paragraph - my($text) = @_; - + #####add sentence breaks as needed##### #non-period end of sentence markers (?!) followed by sentence starters. |