adding GOAL cat

SuperTagger/Linker/utils.py

@@ -38,7 +38,10 @@ def get_axiom_links(max_atoms_in_one_type, atoms_polarity, batch_axiom_links):
 
 def category_to_atoms_axiom_links(category, categories_to_atoms):
     res = [bool(re.match(r'' + atom_type + "_\d+", category)) for atom_type in atom_map.keys()]
-    if True in res:
+    if category.startswith("GOAL:"):
+        word, cat = category.split(':')
+        return [cat]
+    elif True in res:
         return [category]
     else:
         category_cut = regex.match(regex_categories, category).groups()
@@ -65,7 +68,11 @@ def get_atoms_links_batch(category_batch):
 
 def category_to_atoms(category, categories_to_atoms):
     res = [bool(re.match(r'' + atom_type + "_\d+", category)) for atom_type in atom_map.keys()]
-    if True in res:
+    if category.startswith("GOAL:"):
+        word, cat = category.split(':')
+        category = re.match(r'([a-zA-Z|_]+)_\d+', cat).group(1)
+        return [category]
+    elif True in res:
         category = re.match(r'([a-zA-Z|_]+)_\d+', category).group(1)
         return [category]
     else:
@@ -99,7 +106,9 @@ def category_to_atoms_polarity(category, polarity):
     '''
     category_to_polarity = []
     res = [bool(re.match(r'' + atom_type + "_\d+", category)) for atom_type in atom_map.keys()]
-    if True in res or category.startswith("dia") or category.startswith("box"):
+    if category.startswith("GOAL:"):
+        category_to_polarity.append(True)
+    elif True in res or category.startswith("dia") or category.startswith("box"):
         category_to_polarity.append(False)
     else:
         # dr = /

Utils/PostpreprocesTXT.py

@@ -8,14 +8,14 @@ import pandas as pd
 # dl = \
 
 def sub_tree_word(word_with_data: str):
-    s = word_with_data.split('|')
-    try:
+    if word_with_data.startswith("GOAL"):
+        word = word_with_data
+        tree = word_with_data
+    else:
+        s = word_with_data.split('|')
         word = s[0]
         tree = s[1]
-
-        return word, tree
-    except:
-        return s[0], []
+    return word, tree
 
 
 def sub_tree_line(line_with_data: str):

train.py

@@ -61,7 +61,7 @@ print("sentence", sentences_batch[14])
 print("categories ", df_axiom_links["sub_tree"][14])
 print("atoms_batch", atoms_batch[14])
 print("atoms_polarity_batch", atoms_polarity_batch[14])
-print(" truth_links_batch example on a sentence class n", truth_links_batch[14][2])
+print(" truth_links_batch example on a sentence class txt", truth_links_batch[14][16])
 
 
 # Construction tensor dataset