changed default tagger and tag validation RegExp

anarchivist · Feb 1, 2011 · 7559d18 · 7559d18
1 parent 0600a6b
commit 7559d18
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/config.yaml b/config.yaml
@@ -20,6 +20,6 @@ extraction:
     ngramMax: 1
     minWordSize: 3
     # under "basedirectory" directory, delete this file to regenerate a new one
-    tagger: "conll2000_brill_aubt.pickle"
+    tagger: "conll2000_aubt.pickle"
     # Reg Expression for NGram extraction
-    postag_valid: '^((VB,|VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?,|\?,)(CD.,)?)+?((PREP.?|DET.?,|IN.?,|CC.?,|\?,)((VB,|VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?,|\?,))+?)*?$'
+    postag_valid: '^((VB,|VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?,|\?,)+?(CD.,)?)+?((PREP.?|DET.?,|IN.?,|CC.?,|\?,)((VB,|VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?,|\?,)+?)+?)*?$'