moses-smt/mosesdecoder
1
1
Fork 0
mirror of https://github.com/moses-smt/mosesdecoder.git synced 2024-09-11 11:25:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix detokenising : in abbrev. case suffix case

Browse Source
This commit is contained in:
Flammie Pirinen 2015-04-07 15:51:29 +01:00
parent 54e55f2dcb
commit 5817806ec7
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/tokenizer/detokenizer.perl
View File

@ -176,6 +176,10 @@ sub detokenize {
}
} elsif (($language eq "fi") && ($words[$i-1] =~ /:$/) && ($words[$i] =~ /^(N|n|ssa|ssä|a|ä|lla|llä|lta|ltä|lle|ksi|kse)(ni|si|mme|nne|nsa)?(ko|kö|han|hän|pa|pä|kaan|kään|kin)?$/)) {
# Finnish : without intervening space if followed by case suffix
$text=$text.$words[$i];
$prependSpace = " ";
} else {
$text=$text.$prependSpace.$words[$i];
$prependSpace = " ";