update experiment

undertheseanlp · Dec 26, 2018 · d89026a · d89026a
1 parent 67b8497
commit d89026a
Showing 1 changed file with 15 additions and 14 deletions.
diff --git a/egs/vlsp2013_crf/train.py b/egs/vlsp2013_crf/train.py
@@ -8,14 +8,15 @@
 features = [
     "T[-2].lower", "T[-1].lower", "T[0].lower", "T[1].lower", "T[2].lower",
 
-    # "T[-1].isdigit", "T[0].isdigit", "T[1].isdigit",
-    #
-    # "T[-1].istitle", "T[0].istitle", "T[1].istitle",
-    # "T[0,1].istitle", "T[0,2].istitle",
-
-    # "T[-2].is_in_dict", "T[-1].is_in_dict", "T[0].is_in_dict", "T[1].is_in_dict", "T[2].is_in_dict",
-    # "T[-2,-1].is_in_dict", "T[-1,0].is_in_dict", "T[0,1].is_in_dict", "T[1,2].is_in_dict",
-    # "T[-2,0].is_in_dict", "T[-1,1].is_in_dict", "T[0,2].is_in_dict",
+    "T[-1].isdigit", "T[0].isdigit", "T[1].isdigit",
+
+    "T[-1].istitle", "T[0].istitle", "T[1].istitle",
+    "T[0,1].istitle", "T[0,2].istitle",
+
+    "T[-2].is_in_dict", "T[-1].is_in_dict", "T[0].is_in_dict", "T[1].is_in_dict", "T[2].is_in_dict",
+    "T[-2,-1].is_in_dict", "T[-1,0].is_in_dict", "T[0,1].is_in_dict", "T[1,2].is_in_dict",
+    "T[-2,0].is_in_dict", "T[-1,1].is_in_dict", "T[0,2].is_in_dict",
+
     "T[-2,-1].lower", "T[-1,0].lower", "T[0,1].lower", "T[1,2].lower",
     # word unigram and bigram and trigram
     "T[-2]", "T[-1]", "T[0]", "T[1]", "T[2]",
@@ -26,11 +27,11 @@
 trainer = Trainer(tagger, corpus)
 
 params = {
-            'c1': 1.0,  # coefficient for L1 penalty
-            'c2': 1e-3,  # coefficient for L2 penalty
-            'max_iterations': 1000,  #
-            # include transitions that are possible, but not observed
-            'feature.possible_transitions': True,
-            'feature.possible_states': True,
+    'c1': 1.0,  # coefficient for L1 penalty
+    'c2': 1e-3,  # coefficient for L2 penalty
+    'max_iterations': 1000,  #
+    # include transitions that are possible, but not observed
+    'feature.possible_transitions': True,
+    'feature.possible_states': True,
 }
 trainer.train(params)