Update app.py

app.py

@@ -68,23 +68,30 @@ def get_named_entities(text):
         return []
 
 def generate_question_from_sentence(sentence):
-    """Generate a question from a sentence with robust error handling."""
+    """Generate a question from a sentence with improved question formation."""
     try:
         # Remove punctuation at the end
         sentence = re.sub(r'[.!?]$', '', sentence)
         
-        # Check for common patterns that can be turned into questions
-        if re.search(r'\bis\s|\bwas\s|\bwere\s|\bare\s', sentence):
-            # Convert statements with "is", "was", "were", "are" into yes/no questions
-            match = re.search(r'^(.*?)\s(is|was|were|are)\s(.*?)$', sentence, re.IGNORECASE)
-            if match:
-                return f"{match.group(2).capitalize()} {match.group(1)} {match.group(3)}?"
+        # Convert statements with be-verbs into yes/no questions
+        be_verb_pattern = re.search(r'^(.*?)\s(is|was|were|are|am)\s(.*?)$', sentence, re.IGNORECASE)
+        if be_verb_pattern:
+            return f"{be_verb_pattern.group(2).capitalize()} {be_verb_pattern.group(1)} {be_verb_pattern.group(3)}?"
         
-        # Check for sentences with dates or years
+        # Check for modal verbs
+        modal_pattern = re.search(r'^(.*?)\s(can|could|will|would|should|may|might)\s(.*?)$', sentence, re.IGNORECASE)
+        if modal_pattern:
+            return f"{modal_pattern.group(2).capitalize()} {modal_pattern.group(1)} {modal_pattern.group(3)}?"
+        
+        # Check for sentences with temporal markers
         if re.search(r'\b(in|on|during)\s\d{4}\b|\b(January|February|March|April|May|June|July|August|September|October|November|December)\b', sentence, re.IGNORECASE):
             return f"When did {sentence.lower()}?"
         
-        # Try to get named entities, but don't fail if NER isn't working
+        # Check for causal relationships
+        if re.search(r'\bbecause\b|\bdue to\b|\bas a result\b|\btherefore\b|\bhence\b', sentence, re.IGNORECASE):
+            return f"Why {sentence.lower()}?"
+        
+        # Try to get named entities
         entities = get_named_entities(sentence)
         
         # If there are named entities, ask about them
@@ -96,31 +103,47 @@ def generate_question_from_sentence(sentence):
                 return f"Where is {entity}?"
             elif entity_type == 'ORGANIZATION':
                 return f"What is {entity}?"
+            else:
+                return f"Can you tell me more about {entity}?"
         
-        # Check for sentences with "because", "due to", "as a result"
-        if re.search(r'\bbecause\b|\bdue to\b|\bas a result\b', sentence, re.IGNORECASE):
-            return f"Why {sentence.lower()}?"
+        # Check for quantifiable content
+        if re.search(r'\b(many|number of|several|few|multiple)\b', sentence, re.IGNORECASE):
+            return f"How many are mentioned in the statement: '{sentence}'?"
         
-        # Simplified approach without relying on POS tagging
+        # Look for action verbs to create "what" questions
         words = sentence.split()
-        
-        # Very simple subject extraction (first word)
-        if words:
-            subject = words[0]
-            if subject.lower() in ['i', 'you', 'we', 'they', 'he', 'she', 'it', 'this', 'that']:
-                return f"What did {subject.lower()} do?"
+        if len(words) >= 3:
+            # Basic subject-verb detection
+            potential_subject = words[0]
+            potential_verb = words[1]
+            
+            # Common pronouns and determiners
+            pronouns = ['i', 'you', 'we', 'they', 'he', 'she', 'it', 'this', 'that', 'these', 'those', 'a', 'an', 'the']
+            
+            if potential_subject.lower() in pronouns:
+                return f"What did {potential_subject.lower()} {' '.join(words[1:])}?"
             else:
-                return f"What about {subject}?"
+                # Try to identify the main topic
+                # First, remove common stop words
+                stop_words = ['a', 'an', 'the', 'and', 'but', 'or', 'for', 'nor', 'on', 'at', 'to', 'from', 'by']
+                content_words = [word for word in words if word.lower() not in stop_words]
+                
+                if content_words:
+                    main_topic = content_words[0]
+                    return f"What is significant about {main_topic}?"
         
-        # Very generic fallback
+        # More varied generic fallbacks
         question_starters = [
-            "What is described in",
-            "What is mentioned about",
-            "Can you explain",
-            "Could you elaborate on"
+            "What is important about",
+            "How would you describe",
+            "What are the key aspects of",
+            "What's notable regarding",
+            "How does the text characterize",
+            "What insights can be drawn from"
         ]
         
-        return f"{random.choice(question_starters)} the statement: '{sentence}'?"
+        return f"{random.choice(question_starters)} this: '{sentence}'?"
+    
     except Exception as e:
         print(f"Question generation failed: {str(e)}")
         return f"What can you tell me about: '{sentence}'?"