diff options
| author | Chris Dyer <cdyer@cs.cmu.edu> | 2011-01-13 18:43:36 -0500 |
|---|---|---|
| committer | Chris Dyer <cdyer@cs.cmu.edu> | 2011-01-13 18:43:36 -0500 |
| commit | 0ae0a535ddca7d85894c48722fc90c488cc059cb (patch) | |
| tree | a2db11386cea809d13c8d1fee2b12f7dbc2243bd /compound-split/compound-split.pl | |
| parent | b85986c762bc8a2a74bfe0e2eb1d88fba991d554 (diff) | |
updated training data, retrained de seg model
Diffstat (limited to 'compound-split/compound-split.pl')
| -rwxr-xr-x | compound-split/compound-split.pl | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/compound-split/compound-split.pl b/compound-split/compound-split.pl index 490a5bc5..7f45d345 100755 --- a/compound-split/compound-split.pl +++ b/compound-split/compound-split.pl @@ -62,7 +62,7 @@ while(<STDIN>) { my @todo = (); for (my $i=0; $i < scalar @words; $i++) { my $word = lc $words[$i]; - if (length($word)<6 || $word =~ /^[,\-0-9\.]+$/) { + if (length($word)<6 || $word =~ /^[,\-0-9\.]+$/ || $word =~ /[@.\-\/:]/) { if ($IS_PLF) { push @res, "(('" . escape($word) . "',0,1),),"; } else { |