Update app.py

app.py

@@ -12,7 +12,6 @@ nltk.download('punkt')
 
 # load the spacy model
 spacy.cli.download("en_core_web_sm")
-spacy.cli.download("en_core_web_lg")
 
 # use spacy small because in that way we are closer to a BOW model which is the one we care in our case since we just compare words
 nlp = spacy.load('en_core_web_sm', disable=["parser", "ner"])
@@ -24,6 +23,7 @@ def find_comptives_symbols(sentence):
     If more than one symbols exist, return []
     """
 
+    # symbols regex pattern
     pattern = r"(?<![<=>])[%s](?![<=>])" % (re.escape("<=>"))
     matches = re.findall(pattern, sentence)
 
@@ -38,7 +38,7 @@ def find_comptives_symbols(sentence):
 
 def find_comptives_straight_patterns(sentence):
     """
-    Function to identivy mentions of compartives. The form is "comparative adverbs/adjectives followed by than", "words like more/less followed by than", "equal to" 
+    Function to identivy mentions of comparatives. The form is "comparative adverbs/adjectives followed by than", "words like more/less followed by than", "equal to" 
     """
 
     doc = nlp(sentence)
@@ -113,7 +113,6 @@ def find_comptives_straight_patterns(sentence):
     return comparatives
 
 
-
 # helper functions for 'identify_pattern_bigger_smaller'
 
 def identify_comparison(sentence):
@@ -319,7 +318,7 @@ def find_equal_to_comptives_ngrams(sentence):
               similarity = sentence_ngram_doc.similarity(emb_ref)
 
               if similarity >= max_similarity:
-                  possible_reference_list.append({'comparative': [sentence_ngram_str, emb_ref, similarity, "="]})
+                  possible_reference_list.append({'comparative': [sentence_ngram_str, "="]})
                   break
 
     # if we have found a possible refernce that is similar enough with an n-gram of the input sentence, return the comparative '=', otherwise return 0
@@ -329,6 +328,7 @@ def find_equal_to_comptives_ngrams(sentence):
       return []
 
 
+
 def single_verb_comptives(sentence):
     """
     This function takes a sentence and identifies any mention of bigger than, smaller than, equal to, expressed
@@ -363,10 +363,22 @@ def single_verb_comptives(sentence):
                         break
 
                     elif any(lemma in equal_references_sg for lemma in syn.lemma_names()):
-                        # print(lemma)
                         equal_list.append({'comparative': [token.text, "="]})
                         break
 
+                # for syn in synsets:
+                #     antonyms = syn.lemmas()[0].antonyms()
+
+                #     if antonyms and any(lemma in bigger_references_sg for lemma in antonyms[0].name()):
+                #       return 0
+
+                #     elif antonyms and any(lemma in lesser_references_sg for lemma in antonyms[0].name()):
+                #       return 0
+
+
+                #     elif antonyms and any(lemma in equal_references_sg for lemma in antonyms[0].name()):
+                #       return 0
+
     final_list = bigger_list + smaller_list + equal_list
 
     if final_list:
@@ -503,6 +515,7 @@ def multiword_verb_comptives(sentence):
     return bigger_l + smaller_l + equal_l
 
 
+
 def identify_comparatives(sentence):
     """
     This function combines the results of all the aforementioned techniques (simple and advance) to identify bigger than, smaller than, equal to patterns
@@ -535,55 +548,74 @@ def identify_comparatives(sentence):
     return unique_output
 
 
-def magnitude_binding(sentence):
-  
-  comparative_symbols = find_comptives_symbols(sentence)
-  comparative_mentions = identify_comparatives(sentence)
 
-  # starting with the symbols, if one was captured 
-  if len(comparative_symbols) == 1:
+def comparatives_binding(sentence):
 
-    # if the rest of the functions are empty (meaning that there are no other references)
-    if len(comparative_mentions) == 0:
-      return comparative_symbols
+  try:    
+    comparative_symbols = find_comptives_symbols(sentence)
+    comparative_mentions = identify_comparatives(sentence)
 
-  # in case that there is no symbol
-  elif len(comparative_symbols) == 0:
+    # starting with the symbols, if one was captured 
+    if len(comparative_symbols) == 1:
 
-    # we need only one mention of comparatives
-    if len(comparative_mentions) == 1:
-      return comparative_mentions
+      # if the rest of the functions are empty (meaning that there are no other references)
+      if len(comparative_mentions) == 0:
+        return comparative_symbols
 
+      else:
+        return (0, "COMPARATIVES", "more_comparatives_mentions")
+
+    # in case that there is no symbol
+    elif len(comparative_symbols) == 0:
+
+      # we need only one mention of comparatives
+      if len(comparative_mentions) == 1:
+        return comparative_mentions
+
+      # case of no comparative mentions
+      elif len(comparative_mentions) == 0:
+        return (0, "COMPARATIVES", "no_comparatives")
+
+      # case of no more than one comparative mentions
+      else:
+        return (0, "COMPARATIVES", "more_comparatives_mentions")
+
+    # case of multiple symbol references
     else:
-      return 0
+      return (0, "COMPARATIVES", "more_symbol_comparatives")
 
-  # case of multiple symbol references
-  else:
-    return 0
+  except:
+    return (0, "COMPARATIVES", "unknown_error")
 
 
 
 from transformers import pipeline
 import gradio as gr
 
-title = "Natural Language module Demo for Comparatives identification"
-description = "This is a simple demo just for demonstration purposes, so that Serco team might have the chance to validate the results of the Natural Language module concerning the comparatives identification, while in progress"
+title = "Comparatives Demo"
+description = "This is a simple demo just for demonstration purposes for Serco team, to validate the results of the Natural Language module concerning comparatives identification, while in progress"
 
 examples = [
-    ["earthquake located in Ishkoshim higher than 5, Tajikistan in May the ninth with magnitude equal to 6.2"],
-    ["earthquake located in Ishkoshim, Tajikistan in May the ninth with magnitude < 6.2"],
-    ["earthquake located in Ishkoshim that is > than the one in Rome, and < than 8.2"],
-    ["earthquake located in Ishkoshim, Tajikistan in May the ninth with magnitude lesser than 6.2"],
-    ["earthquake located in Ishkoshim, Tajikistan in May the ninth with magnitude same with 6.2"],
-    ["I want an earthquake that happend in Rome during 2016 with a magnitude dallying of 5."],
-    ["I want an earthquake that happend in Rome during 2016 and surpassed the magnitude of 5."],
-    ["I want an earthquake that happend in Rome during 2016 with a magnitude similar to 5."],
-    ["I want an earthquaqe event that happend in Italy, Rome during 2016 February with a magnitude that was in a par with 5."]
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude > 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude = 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude bigger than 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude more than 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude higher than 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude smaller than 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude lesser than 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude equal to 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude equivalent to 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude surpassing 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude lagging of 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude that matches 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude that is superior of 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude that is inferior of 6.2"],
+    ["I want an earthquake that is located in Rome, Italy on 01/01/23 with magnitude that is in line with 6.2"]
 ]
 
 
 gr.Interface(
-    fn=magnitude_binding, 
+    fn=comparatives_binding, 
     inputs="text", 
     outputs="text",
     title=title,