Update app.py

app.py

@@ -6,7 +6,6 @@ import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
-import random  # Import random for versatile synonym replacement
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -30,7 +29,7 @@ def predict_en(text):
     res = pipeline_en(text)[0]
     return res['label'], res['score']
 
-# Enhanced function to get synonyms using NLTK WordNet
+# Function to get synonyms using NLTK WordNet
 def get_synonyms_nltk(word, pos):
     synsets = wordnet.synsets(word, pos=pos)
     if synsets:
@@ -38,73 +37,23 @@ def get_synonyms_nltk(word, pos):
         return [lemma.name() for lemma in lemmas]
     return []
 
-# Retain the structure of the input text (headings, paragraphs, line breaks)
-def retain_structure(text):
-    lines = text.split("\n")
-    formatted_lines = []
+# Function to dynamically select the most relevant synonym
+def get_relevant_synonym(word, pos, context):
+    synonyms = get_synonyms_nltk(word, pos)
+    if not synonyms:
+        return word
     
-    for line in lines:
-        if line.strip().isupper():  # Heading if all caps
-            formatted_lines.append(f"# {line.strip()}")  # Treat it as a heading
-        else:
-            formatted_lines.append(line)  # Otherwise, it's a paragraph or normal text
+    # Basic relevance check: choose the synonym that appears most frequently in similar contexts
+    relevant_synonym = word
+    max_count = 0
     
-    return "\n".join(formatted_lines)
-
-# Dynamic and versatile synonym replacement
-def replace_with_synonym(token):
-    pos = None
-    if token.pos_ == "VERB":
-        pos = wordnet.VERB
-    elif token.pos_ == "NOUN":
-        pos = wordnet.NOUN
-    elif token.pos_ == "ADJ":
-        pos = wordnet.ADJ
-    elif token.pos_ == "ADV":
-        pos = wordnet.ADV
-    
-    synonyms = get_synonyms_nltk(token.lemma_, pos)
+    for synonym in synonyms:
+        count = context.lower().count(synonym.lower())
+        if count > max_count:
+            max_count = count
+            relevant_synonym = synonym
     
-    if synonyms:
-        # Randomly choose a synonym to add more versatility
-        synonym = random.choice(synonyms)
-        if token.tag_ == "VBG":  # Present participle (e.g., running)
-            synonym = synonym + 'ing'
-        elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
-            synonym = synonym + 'ed'
-        elif token.tag_ == "VBZ":  # Third-person singular present
-            synonym = synonym + 's'
-        return synonym
-    return token.text
-
-# Function to rephrase text and replace words with versatile synonyms
-def rephrase_with_synonyms(text):
-    doc = nlp(text)
-    rephrased_text = []
-
-    for token in doc:
-        pos_tag = None
-        if token.pos_ == "NOUN":
-            pos_tag = wordnet.NOUN
-        elif token.pos_ == "VERB":
-            pos_tag = wordnet.VERB
-        elif token.pos_ == "ADJ":
-            pos_tag = wordnet.ADJ
-        elif token.pos_ == "ADV":
-            pos_tag = wordnet.ADV
-        
-        if pos_tag:
-            synonyms = get_synonyms_nltk(token.text, pos_tag)
-            if synonyms:
-                # Use the dynamic synonym replacement for versatility
-                synonym = replace_with_synonym(token)
-                rephrased_text.append(synonym)
-            else:
-                rephrased_text.append(token.text)
-        else:
-            rephrased_text.append(token.text)
-
-    return ' '.join(rephrased_text)
+    return relevant_synonym
 
 # Function to remove redundant and meaningless words
 def remove_redundant_words(text):
@@ -202,6 +151,34 @@ def correct_article_errors(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
+# Function to get the correct synonym while maintaining verb form
+def replace_with_synonym(token, context):
+    pos = None
+    if token.pos_ == "VERB":
+        pos = wordnet.VERB
+    elif token.pos_ == "NOUN":
+        pos = wordnet.NOUN
+    elif token.pos_ == "ADJ":
+        pos = wordnet.ADJ
+    elif token.pos_ == "ADV":
+        pos = wordnet.ADV
+    
+    synonyms = get_synonyms_nltk(token.lemma_, pos)
+    
+    if synonyms:
+        synonym = get_relevant_synonym(token.text, pos, context)
+        if token.pos_ == "VERB":
+            if token.tag_ == "VBG":  # Present participle (e.g., running)
+                synonym = synonym + 'ing'
+            elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
+                synonym = synonym + 'ed'
+            elif token.tag_ == "VBZ":  # Third-person singular present
+                synonym = synonym + 's'
+        elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
+            synonym += 's' if not synonym.endswith('s') else ""
+        return synonym
+    return token.text
+
 # Function to check for and avoid double negatives
 def correct_double_negatives(text):
     doc = nlp(text)
@@ -235,6 +212,56 @@ def correct_spelling(text):
         corrected_words.append(corrected_word)
     return ' '.join(corrected_words)
 
+# Function to rephrase text and replace words with their synonyms while maintaining form
+def rephrase_with_synonyms(text):
+    doc = nlp(text)
+    rephrased_text = []
+
+    for token in doc:
+        pos_tag = None
+        if token.pos_ == "NOUN":
+            pos_tag = wordnet.NOUN
+        elif token.pos_ == "VERB":
+            pos_tag = wordnet.VERB
+        elif token.pos_ == "ADJ":
+            pos_tag = wordnet.ADJ
+        elif token.pos_ == "ADV":
+            pos_tag = wordnet.ADV
+        
+        if pos_tag:
+            synonyms = get_synonyms_nltk(token.text, pos_tag)
+            if synonyms:
+                synonym = get_relevant_synonym(token.text, pos_tag, text)
+                if token.pos_ == "VERB":
+                    if token.tag_ == "VBG":  # Present participle (e.g., running)
+                        synonym = synonym + 'ing'
+                    elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
+                        synonym = synonym + 'ed'
+                    elif token.tag_ == "VBZ":  # Third-person singular present
+                        synonym = synonym + 's'
+                elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
+                    synonym += 's' if not synonym.endswith('s') else ""
+                rephrased_text.append(synonym)
+            else:
+                rephrased_text.append(token.text)
+        else:
+            rephrased_text.append(token.text)
+
+    return ' '.join(rephrased_text)
+
+# Function to retain the structure of the input text (headings, paragraphs, line breaks)
+def retain_structure(text):
+    lines = text.split("\n")
+    formatted_lines = []
+    
+    for line in lines:
+        if line.strip().isupper():  # Heading if all caps
+            formatted_lines.append(f"# {line.strip()}")  # Treat it as a heading
+        else:
+            formatted_lines.append(line)  # Otherwise, it's a paragraph or normal text
+    
+    return "\n".join(formatted_lines)
+
 # Function to paraphrase and correct grammar with enhanced accuracy and retain structure
 def paraphrase_and_correct(text):
     # Retain the structure (headings, paragraphs, line breaks)
@@ -259,13 +286,16 @@ def paraphrase_and_correct(text):
     paraphrased_text = correct_double_negatives(paraphrased_text)
     paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
     
-    # Rephrase with versatile synonyms while maintaining grammatical forms
+    # Rephrase with synonyms while maintaining grammatical forms
     paraphrased_text = rephrase_with_synonyms(paraphrased_text)
     
     # Correct spelling errors
     paraphrased_text = correct_spelling(paraphrased_text)
     
-    return paraphrased_text
+    # Reapply the structure to the final output
+    final_output = retain_structure(paraphrased_text)
+    
+    return final_output
 
 # Gradio app setup with two tabs
 with gr.Blocks() as demo:
@@ -279,8 +309,8 @@ with gr.Blocks() as demo:
         button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
 
     with gr.Tab("Paraphrasing & Grammar Correction"):
-        t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction')
-        button2 = gr.Button("🔄 Paraphrase and Correct")
+        t2 = gr.Textbox(lines=5, label='Enter text for Humanifying')
+        button2 = gr.Button("🔄 Humanifier")
         result2 = gr.Textbox(lines=5, label='Corrected Text')
 
         # Connect the paraphrasing and correction function to the button