Update app.py

app.py

@@ -5,7 +5,6 @@ import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
-from collections import defaultdict
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -29,12 +28,10 @@ except OSError:
 # Function to get synonyms using NLTK WordNet (Humanifier)
 def get_synonyms_nltk(word, pos):
     synsets = wordnet.synsets(word, pos=pos)
-    synonyms = set()
-    for synset in synsets:
-        for lemma in synset.lemmas():
-            if lemma.name() != word:
-                synonyms.add(lemma.name())
-    return list(synonyms)
+    if synsets:
+        lemmas = synsets[0].lemmas()
+        return [lemma.name() for lemma in lemmas]
+    return []
 
 # Function to capitalize the first letter of sentences and proper nouns (Humanifier)
 def capitalize_sentences_and_nouns(text):
@@ -54,69 +51,53 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-# Function to correct tense errors in a sentence (Tense Correction)
+# Improved Function to correct tense errors in a sentence (Tense Correction)
 def correct_tense_errors(text):
     doc = nlp(text)
     corrected_text = []
-
     for token in doc:
         if token.pos_ == "VERB":
-            # Check if verb is in its base form
-            if token.tag_ == "VB" and token.text.lower() not in ["be", "have", "do"]:
-                # Attempt to correct verb form based on sentence context
-                context = " ".join([t.text for t in doc if t.i != token.i])
-                corrected_text.append(token.lemma_)
+            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
+            if token.tag_ in {"VB", "VBP"}:  # Present tense verb correction
+                corrected_text.append(lemma)
+            elif token.tag_ in {"VBD", "VBN"}:  # Past tense correction
+                corrected_text.append(lemma + "ed")
             else:
                 corrected_text.append(token.text)
         else:
             corrected_text.append(token.text)
-
     return ' '.join(corrected_text)
 
-# Function to correct singular/plural errors (Singular/Plural Correction)
+# Improved Function to correct singular/plural errors (Singular/Plural Correction)
 def correct_singular_plural_errors(text):
     doc = nlp(text)
     corrected_text = []
-
-    # Create a context dictionary for singular/plural determination
-    context = defaultdict(int)
-    for token in doc:
-        if token.pos_ == "NOUN":
-            # Track context for noun usage
-            if token.tag_ == "NNS":
-                context['plural'] += 1
-            elif token.tag_ == "NN":
-                context['singular'] += 1
-
+    
     for token in doc:
         if token.pos_ == "NOUN":
-            if token.tag_ == "NN":  # Singular noun
-                if context['plural'] > context['singular']:
-                    corrected_text.append(token.lemma_ + 's')
-                else:
-                    corrected_text.append(token.text)
-            elif token.tag_ == "NNS":  # Plural noun
-                if context['singular'] > context['plural']:
-                    corrected_text.append(token.lemma_)
-                else:
-                    corrected_text.append(token.text)
+            if token.tag_ == "NN" and token.head.pos_ == "VERB" and token.head.tag_ == "VBZ":  # Singular noun with singular verb
+                corrected_text.append(token.text + 's')  # Make plural
+            elif token.tag_ == "NNS" and token.head.pos_ == "VERB" and token.head.tag_ == "VBP":  # Plural noun with plural verb
+                corrected_text.append(token.lemma_)  # Correct to singular
             else:
                 corrected_text.append(token.text)
         else:
             corrected_text.append(token.text)
-
+    
     return ' '.join(corrected_text)
 
-# Function to check and correct article errors
+# Improved Function to check and correct article errors
 def correct_article_errors(text):
     doc = nlp(text)
     corrected_text = []
-    for token in doc:
-        if token.text in ['a', 'an']:
+    vowels = "aeiou"
+    for i, token in enumerate(doc):
+        if token.text.lower() in ['a', 'an']:
             next_token = token.nbor(1)
-            if token.text == "a" and next_token.text[0].lower() in "aeiou":
+            next_word_lemma = next_token.lemma_ if next_token.lemma_ else next_token.text
+            if token.text == "a" and next_word_lemma[0].lower() in vowels:
                 corrected_text.append("an")
-            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
+            elif token.text == "an" and next_word_lemma[0].lower() not in vowels:
                 corrected_text.append("a")
             else:
                 corrected_text.append(token.text)
@@ -124,32 +105,33 @@ def correct_article_errors(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-# Paraphrasing function using SpaCy and NLTK (Humanifier)
+# Enhanced Paraphrasing function using SpaCy and NLTK (Humanifier)
 def paraphrase_with_spacy_nltk(text):
     doc = nlp(text)
     paraphrased_words = []
     
     for token in doc:
-        # Map SpaCy POS tags to WordNet POS tags
         pos = None
-        if token.pos_ == "NOUN":
+        if token.pos_ in {"NOUN"}:
             pos = wordnet.NOUN
-        elif token.pos_ == "VERB":
+        elif token.pos_ in {"VERB"}:
             pos = wordnet.VERB
-        elif token.pos_ == "ADJ":
+        elif token.pos_ in {"ADJ"}:
             pos = wordnet.ADJ
-        elif token.pos_ == "ADV":
+        elif token.pos_ in {"ADV"}:
             pos = wordnet.ADV
         
         synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
         
-        # Replace with a synonym only if it makes sense
-        if synonyms:
+        # Replace with a synonym only if it makes sense contextually
+        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
             paraphrased_words.append(synonyms[0])
         else:
             paraphrased_words.append(token.text)
     
-    return ' '.join(paraphrased_words)
+    paraphrased_sentence = ' '.join(paraphrased_words)
+    
+    return paraphrased_sentence
 
 # Combined function: Paraphrase -> Grammar Correction -> Capitalization (Humanifier)
 def paraphrase_and_correct(text):
@@ -160,6 +142,8 @@ def paraphrase_and_correct(text):
     corrected_text = correct_article_errors(paraphrased_text)
     corrected_text = capitalize_sentences_and_nouns(corrected_text)
     corrected_text = correct_singular_plural_errors(corrected_text)
+    
+    # Step 3: Capitalize sentences and proper nouns (final correction step)
     final_text = correct_tense_errors(corrected_text)
     
     return final_text