[DEBUG] trying to fit 'MElt FR' as a tagger

parsing/NgramsExtractors/EnglishNgramsExtractor.py

 from .NgramsExtractor import NgramsExtractor
-from ..Taggers import NltkTagger
+from ..Taggers import NltkTagger, MeltTagger
 
 
 class EnglishNgramsExtractor(NgramsExtractor):
 
     def start(self):
-        self.tagger = NltkTagger()
-        # self.tagger = MeltTagger(language='en')
+        # self.tagger = NltkTagger()
+        self.tagger = MeltTagger(language='en')
     
\ No newline at end of file

parsing/NgramsExtractors/NgramsExtractor.py

@@ -29,9 +29,9 @@ class NgramsExtractor:
     Returns a list of the ngrams found in the given text.
     """
     def extract_ngrams(self, contents):
-        tagged_ngrams = list(self.tagger.tag_text(contents))
-        if len(tagged_ngrams):
-            grammar_parsed = self._grammar.parse(tagged_ngrams)
+        tagged_tokens = list(self.tagger.tag_text(contents))
+        if len(tagged_tokens):
+            grammar_parsed = self._grammar.parse(tagged_tokens)
             for subtree in grammar_parsed.subtrees():
                 if subtree.label() == self._label:
                     yield subtree.leaves()

parsing/Taggers/MeltTagger.py

@@ -102,7 +102,7 @@ class MeltTagger(Tagger):
                 if len(token.string):
                     yield (token.string, token.label, )
 
-    def tag_text(self, text, lemmatize=True):
+    def tag_text(self, text, lemmatize=False):
         tagged_tokens = self._tag(text)
         # without lemmatization
         if not lemmatize: