import os import gradio as gr from transformers import pipeline import spacy import subprocess import nltk from nltk.corpus import wordnet from spellchecker import SpellChecker import re import inflect try: nlp = spacy.load("en_core_web_sm") except OSError: print("Downloading spaCy model...") spacy.cli.download("en_core_web_sm") nlp = spacy.load("en_core_web_sm") # 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 spell = SpellChecker() # Initialize the inflect engine for pluralization inflect_engine = inflect.engine() # Ensure necessary NLTK data is downloaded nltk.download('wordnet') nltk.download('omw-1.4') # Load the SpaCy model nlp = spacy.load("en_core_web_sm") # Function to predict the label and score for English text (AI Detection) def predict_en(text): res = pipeline_en(text)[0] return res['label'], res['score'] # Function to get synonyms using NLTK WordNet def get_synonyms_nltk(word, pos): synsets = wordnet.synsets(word, pos=pos) if synsets: lemmas = synsets[0].lemmas() return [lemma.name() for lemma in lemmas if lemma.name() != word] return [] # Function to remove redundant and meaningless 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" and token.dep_ in {"aux", "auxpass"}: 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 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 = 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 = synonyms[0] 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 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: 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.append(token.head.lemma_ + "s") elif token.tag_ == "NNS" and token.head.tag_ == "VBZ": # Plural noun, should not use singular verb corrected_text.append(token.head.lemma_) corrected_text.append(token.text) return ' '.join(corrected_text) # 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) return ' '.join(corrected_words) # Function to correct punctuation issues def correct_punctuation(text): text = re.sub(r'\s+([?.!,";:])', r'\1', text) text = re.sub(r'([?.!,";:])\s+', r'\1 ', text) 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) return text # 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: if token.pos_ == "NOUN" and token.text.lower() == "earth": rephrased_text.append("Earth") continue 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.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 (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' rephrased_text.append(synonym) else: rephrased_text.append(token.text) else: rephrased_text.append(token.text) return ' '.join(rephrased_text) # Function to paraphrase and correct grammar with enhanced accuracy def paraphrase_and_correct(text): # Remove meaningless or redundant words first cleaned_text = remove_redundant_words(text) # Capitalize sentences and proper nouns cleaned_text = capitalize_sentences_and_nouns(cleaned_text) # Correct tense errors cleaned_text = correct_tense_errors(cleaned_text) # Correct singular/plural errors cleaned_text = correct_singular_plural_errors(cleaned_text) # Correct article errors cleaned_text = correct_article_errors(cleaned_text) # Correct spelling cleaned_text = correct_spelling(cleaned_text) # Correct punctuation issues cleaned_text = correct_punctuation(cleaned_text) # Handle possessives cleaned_text = handle_possessives(cleaned_text) # Replace words with synonyms cleaned_text = rephrase_with_synonyms(cleaned_text) # Correct double negatives cleaned_text = correct_double_negatives(cleaned_text) # Ensure subject-verb agreement cleaned_text = ensure_subject_verb_agreement(cleaned_text) return cleaned_text # Function to detect AI-generated content def detect_ai(text): label, score = predict_en(text) return label, score # Gradio interface setup def gradio_interface(text): ai_result = detect_ai(text) corrected_text = paraphrase_and_correct(text) return ai_result, corrected_text # Create Gradio interface iface = gr.Interface(fn=gradio_interface, inputs=gr.Textbox(lines=5, placeholder="Enter text here..."), outputs=[gr.Label(num_top_classes=2), gr.Textbox()], title="AI Detection and Grammar Correction", description="Detect AI-generated content and correct grammar issues.") # Launch the app iface.launch()