Update app.py

app.py

@@ -12,7 +12,7 @@ from inflect import engine  # For pluralization
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
 
-# Initialize the spell checker
+# Initialize the spell checker and inflect engine
 spell = SpellChecker()
 inflect_engine = engine()
 
@@ -27,7 +27,7 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Function to predict the label and score for English text (AI Detection)
+# Function to predict AI detection
 def predict_en(text):
     res = pipeline_en(text)[0]
     return res['label'], res['score']
@@ -40,158 +40,23 @@ def get_synonyms_nltk(word, pos):
         return [lemma.name() for lemma in lemmas if lemma.name() != word]  # Avoid original word
     return []
 
-# Function to remove redundant and meaningless words
+# Function to remove redundant words
 def remove_redundant_words(text):
-    doc = nlp(text)
     meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
-    filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
-    return ' '.join(filtered_text)
-
-# Function to capitalize the first letter of sentences and proper nouns
-def capitalize_sentences_and_nouns(text):
-    doc = nlp(text)
-    corrected_text = []
-
-    for sent in doc.sents:
-        sentence = []
-        for token in sent:
-            if token.i == sent.start:  # First word of the sentence
-                sentence.append(token.text.capitalize())
-            elif token.pos_ == "PROPN":  # Proper noun
-                sentence.append(token.text.capitalize())
-            else:
-                sentence.append(token.text)
-        corrected_text.append(' '.join(sentence))
-
-    return ' '.join(corrected_text)
-
-# Function to correct tense errors in a sentence
-def correct_tense_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.pos_ == "VERB":
-            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
-            corrected_text.append(lemma)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-# Function to correct singular/plural errors using inflect
-def correct_singular_plural_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    
-    for token in doc:
-        if token.pos_ == "NOUN":
-            if token.tag_ == "NN":  # Singular noun
-                if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
-                    corrected_text.append(inflect_engine.plural(token.lemma_))
-                else:
-                    corrected_text.append(token.text)
-            elif token.tag_ == "NNS":  # Plural noun
-                if any(child.text.lower() in ['a', 'one'] for child in token.head.children):
-                    corrected_text.append(inflect_engine.singular_noun(token.text) or token.text)
-                else:
-                    corrected_text.append(token.text)
-        else:
-            corrected_text.append(token.text)
-    
-    return ' '.join(corrected_text)
-
-# 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']:
-            next_token = token.nbor(1)
-            if token.text == "a" and next_token.text[0].lower() in "aeiou":
-                corrected_text.append("an")
-            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
-                corrected_text.append("a")
-            else:
-                corrected_text.append(token.text)
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-# Function to get the correct synonym while maintaining verb form
-def replace_with_synonym(token):
-    pos = {
-        "VERB": wordnet.VERB,
-        "NOUN": wordnet.NOUN,
-        "ADJ": wordnet.ADJ,
-        "ADV": wordnet.ADV
-    }.get(token.pos_, None)
-
-    synonyms = get_synonyms_nltk(token.lemma_, pos)
-
-    if synonyms:
-        synonym = synonyms[0]
-        if token.tag_ == "VBG":  # Present participle
-            synonym += 'ing'
-        elif token.tag_ in {"VBD", "VBN"}:  # Past tense or past participle
-            synonym += 'ed'
-        elif token.tag_ == "VBZ":  # Third-person singular present
-            synonym += 's'
-        return synonym
-    return token.text
-
-# Function to check for and avoid double negatives
-def correct_double_negatives(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        if token.text.lower() == "not" and any(child.text.lower() == "never" for child in token.head.children):
-            corrected_text.append("always")
-        else:
-            corrected_text.append(token.text)
-    return ' '.join(corrected_text)
-
-# Function to ensure subject-verb agreement
-def ensure_subject_verb_agreement(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        corrected_text.append(token.text)
-        if token.dep_ == "nsubj" and token.head.pos_ == "VERB":
-            if token.tag_ == "NN" and token.head.tag_ != "VBZ":  # Singular noun, should use singular verb
-                corrected_text[-1] = token.head.lemma_ + "s"
-            elif token.tag_ == "NNS" and token.head.tag_ == "VBZ":  # Plural noun, should not use singular verb
-                corrected_text[-1] = token.head.lemma_
-    return ' '.join(corrected_text)
+    return ' '.join(word for word in text.split() if word.lower() not in meaningless_words)
 
 # Function to correct spelling errors
 def correct_spelling(text):
     words = text.split()
-    corrected_words = []
-    for word in words:
-        corrected_word = spell.correction(word)
-        corrected_words.append(corrected_word if corrected_word else word)  # Keep original if correction is None
+    corrected_words = [spell.correction(word) for word in words]
     return ' '.join(corrected_words)
 
-# Function to correct punctuation issues
-def correct_punctuation(text):
-    text = re.sub(r'\s+([?.!,";:])', r'\1', text)  # Remove space before punctuation
-    text = re.sub(r'([?.!,";:])\s+', r'\1 ', text)  # Ensure a single space after punctuation
-    return text
-
-# Function to ensure correct handling of possessive forms
-def handle_possessives(text):
-    text = re.sub(r"\b(\w+)'s\b", r"\1's", text)  # Preserve possessive forms
-    return text
-
-# Function to rephrase text and replace words with their synonyms while maintaining form
+# Function to rephrase text with synonyms
 def rephrase_with_synonyms(text):
     doc = nlp(text)
     rephrased_text = []
 
     for token in doc:
-        if token.pos_ == "NOUN" and token.text.lower() == "earth":
-            rephrased_text.append("Earth")
-            continue
-        
         pos_tag = {
             "NOUN": wordnet.NOUN,
             "VERB": wordnet.VERB,
@@ -201,74 +66,36 @@ def rephrase_with_synonyms(text):
         
         if pos_tag:
             synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
-            if synonyms:
-                synonym = synonyms[0]  # Just using the first synonym for simplicity
-                if token.pos_ == "VERB":
-                    if token.tag_ == "VBG":  # Present participle
-                        synonym += 'ing'
-                    elif token.tag_ in {"VBD", "VBN"}:  # Past tense or past participle
-                        synonym += 'ed'
-                    elif token.tag_ == "VBZ":  # Third-person singular present
-                        synonym += 's'
-                rephrased_text.append(synonym)
-            else:
-                rephrased_text.append(token.text)
+            synonym = synonyms[0] if synonyms else token.text
+            rephrased_text.append(synonym)
         else:
             rephrased_text.append(token.text)
 
     return ' '.join(rephrased_text)
 
-# Function to paraphrase and correct grammar with enhanced accuracy
+# Function to paraphrase and correct grammar
 def paraphrase_and_correct(text):
-    # Remove meaningless or redundant words first
     cleaned_text = remove_redundant_words(text)
-    
-    # Capitalize sentences and nouns
-    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
-
-    # Correct tense and singular/plural errors
-    paraphrased_text = correct_tense_errors(paraphrased_text)
-    paraphrased_text = correct_singular_plural_errors(paraphrased_text)
-    paraphrased_text = correct_article_errors(paraphrased_text)
-
-    # Correct spelling errors
-    paraphrased_text = correct_spelling(paraphrased_text)
-
-    # Correct punctuation issues
-    paraphrased_text = correct_punctuation(paraphrased_text)
-
-    # Handle possessives
-    paraphrased_text = handle_possessives(paraphrased_text)
-
-    # Ensure subject-verb agreement
-    paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
-
-    # Replace with synonyms
-    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
-
-    # Correct for double negatives
-    paraphrased_text = correct_double_negatives(paraphrased_text)
-
-    return paraphrased_text
+    cleaned_text = correct_spelling(cleaned_text)
+    return rephrase_with_synonyms(cleaned_text)
 
-# Function to handle the user interface
+# Function to handle user input
 def process_text(input_text):
     ai_label, ai_score = predict_en(input_text)
-    ai_result = f"AI Detected: {ai_label} (Score: {ai_score:.2f})"
 
     if ai_label == "HUMAN":
         corrected_text = paraphrase_and_correct(input_text)
-        return corrected_text, ai_result
+        return corrected_text
     else:
-        return "The text seems to be AI-generated; no correction applied.", ai_result
+        return "The text seems to be AI-generated; no correction applied."
 
 # Gradio interface
 iface = gr.Interface(
     fn=process_text,
     inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."),
-    outputs=[gr.Textbox(label="Corrected Text"), gr.Textbox(label="AI Detection Result")],
-    title="Text Correction and AI Detection",
-    description="This app corrects grammar, spelling, and punctuation while also detecting AI-generated content."
+    outputs=gr.Textbox(label="Corrected Text"),
+    title="Text Correction and Rephrasing",
+    description="This app corrects and rephrases text while detecting AI-generated content."
 )
 
 # Launch the interface