diff options
| author | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2014-01-20 00:11:27 -0500 |
|---|---|---|
| committer | Chris Dyer <cdyer@allegro.clab.cs.cmu.edu> | 2014-01-20 00:11:27 -0500 |
| commit | 02a764cc553f238cdd0be4c6dee4ea144cda84ba (patch) | |
| tree | cc1b42844831c2bd190903fe29f6a68cfc41c219 /corpus/tokenize-anything.sh | |
| parent | 54449ce0eb266ac8e1617f6db7f5390b0a3e26ce (diff) | |
hindi edits
Diffstat (limited to 'corpus/tokenize-anything.sh')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh index 5b7933d8..bca954d1 100755 --- a/corpus/tokenize-anything.sh +++ b/corpus/tokenize-anything.sh @@ -14,6 +14,7 @@ fi $SUPPORT/utf8-normalize.sh $NORMARGS | $SUPPORT/quote-norm.pl | $SUPPORT/tokenizer.pl | + $SUPPORT/fix-eos.pl | sed $SEDFLAGS -e 's/ al - / al-/g' | $SUPPORT/fix-contract.pl | sed $SEDFLAGS -e 's/^ //' | sed $SEDFLAGS -e 's/ $//' | |