moses-smt/mosesdecoder
1
1
Fork 0
mirror of https://github.com/moses-smt/mosesdecoder.git synced 2024-08-16 23:10:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

revert 05788925

Browse Source
This commit is contained in:
Barry Haddow 2019-09-30 16:53:06 +01:00
parent 257d7e5e66
commit 9bffde57ba
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/ems/support/split-sentences.perl
View File

@ -202,7 +202,7 @@ sub preprocess {
my $starting_punct = $2;
if ($prefix && $NONBREAKING_PREFIX{$prefix} && $NONBREAKING_PREFIX{$prefix} == 1 && !$starting_punct) {
# Not breaking;
} elsif ($words[$i] =~ /(\.?)[\p{IsUpper}\-]+(\.+)$/) {
} elsif ($words[$i] =~ /(\.)[\p{IsUpper}\-]+(\.+)$/) {
# Not breaking - upper case acronym
} elsif($words[$i+1] =~ /^([ ]*[\'\"\(\[\¿\¡\p{IsPi}]*[ ]*[\p{IsUpper}0-9])/) {
# The next word has a bunch of initial quotes, maybe a