checked >100 penn words in DictFin

2013-04-04 19:11:17 +00:00
parent e6e64abb3c
commit a4694ada95
3 changed files with 244 additions and 237 deletions
--- a/lib/src/finnish/stemmed/DictEngFin.gf
+++ b/lib/src/finnish/stemmed/DictEngFin.gf
--- a/lib/src/finnish/stemmed/ElimPredef.hs
+++ b/lib/src/finnish/stemmed/ElimPredef.hs
@@ -3,7 +3,7 @@ import qualified Data.Set as S
 -- comment out words that are predefined in another lexicon
 -- runghc ElimPredef.hs <DictEngFin.gf
 removeFile = "todo.txt"
-removeMsg = "MANUAL5_3"
+removeMsg = "MMMM"

 -- also used for temporarily eliminating whatever from compilation
 --removeFile = "commentOut"
--- a/lib/src/finnish/stemmed/log.txt
+++ b/lib/src/finnish/stemmed/log.txt
@@ -235,4 +235,8 @@ Checked words:

 as of version 17-.

+Prepared a list ToCheckFin.gf (in MOLTO svn) for checking the top-3000
+Penn words, which occur >9 times. Went through >99, with 260 changes
+in test corpus as result. Version 18-
+