Spaces:
Sleeping
Sleeping
| # Added more redundant/filler words | |
| def remove_redundant_words(text): | |
| doc = nlp(text) | |
| meaningless_words = {"actually", "basically", "literally", "really", "very", "just", "quite", "rather", "simply", "that", "kind of", "sort of", "you know", "honestly", "seriously"} | |
| filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words] | |
| return ' '.join(filtered_text) | |
| # Capitalize 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 or token.pos_ == "PROPN": | |
| sentence.append(token.text.capitalize()) | |
| else: | |
| sentence.append(token.text.lower()) | |
| corrected_text.append(' '.join(sentence)) | |
| return ' '.join(corrected_text) | |
| # Function to dynamically correct tenses and verb forms | |
| 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) | |
| # Enhanced function to handle 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": | |
| corrected_text.append(token.head.lemma_ + "s") | |
| elif token.tag_ == "NNS" and token.head.tag_ == "VBZ": | |
| corrected_text.append(token.head.lemma_) | |
| else: | |
| corrected_text.append(token.head.text) | |
| else: | |
| corrected_text.append(token.text) | |
| return ' '.join(corrected_text) | |
| # Ensure proper apostrophe usage and possessives | |
| def correct_apostrophes(text): | |
| text = re.sub(r"\b(\w+)s\b(?<!\'s)", r"\1's", text) # Simple apostrophe correction | |
| text = re.sub(r"\b(\w+)s'\b", r"\1s'", text) # Handles plural possessives | |
| return text | |
| # Enhanced punctuation | |
| def enhance_punctuation(text): | |
| text = re.sub(r'\s+([?.!,";:])', r'\1', text) # Remove extra space before punctuation | |
| text = re.sub(r'([?.!,";:])(\S)', r'\1 \2', text) # Add space after punctuation if needed | |
| return text | |
| # Paraphrasing using synonyms and correcting semantic errors | |
| def rephrase_with_synonyms(text): | |
| doc = nlp(text) | |
| rephrased_text = [] | |
| for token in doc: | |
| pos_tag = None | |
| if token.pos_ in ["NOUN", "VERB", "ADJ", "ADV"]: | |
| pos_tag = getattr(wordnet, token.pos_) | |
| if pos_tag: | |
| synonyms = get_synonyms_nltk(token.lemma_, pos_tag) | |
| if synonyms: | |
| synonym = synonyms[0] | |
| if token.pos_ == "VERB": | |
| if token.tag_ == "VBG": | |
| synonym = synonym + 'ing' | |
| elif token.tag_ in ["VBD", "VBN"]: | |
| synonym = synonym + 'ed' | |
| elif token.tag_ == "VBZ": | |
| synonym = synonym + 's' | |
| rephrased_text.append(synonym) | |
| else: | |
| rephrased_text.append(token.text) | |
| else: | |
| rephrased_text.append(token.text) | |
| return ' '.join(rephrased_text) | |
| # Comprehensive text correction | |
| def paraphrase_and_correct(text): | |
| text = enhanced_spell_check(text) | |
| text = remove_redundant_words(text) | |
| text = capitalize_sentences_and_nouns(text) | |
| text = correct_tense_errors(text) | |
| text = correct_singular_plural_errors(text) | |
| text = correct_article_errors(text) | |
| text = enhance_punctuation(text) | |
| text = correct_apostrophes(text) | |
| text = rephrase_with_synonyms(text) | |
| text = correct_double_negatives(text) | |
| text = ensure_subject_verb_agreement(text) | |
| return text | |
| # Integrate with Gradio UI | |
| def gradio_interface(text): | |
| corrected_text = paraphrase_and_correct(text) | |
| return corrected_text | |
| iface = gr.Interface( | |
| fn=gradio_interface, | |
| inputs=gr.Textbox(lines=5, placeholder="Enter text here..."), | |
| outputs=[gr.Textbox(label="Corrected Text")], | |
| title="Grammar & Semantic Error Correction", | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() | |