sashtech's picture
Update app.py
5cbdb52 verified
raw
history blame
3.27 kB
import gradio as gr
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet
# Ensure necessary NLTK data is downloaded
nltk.download('wordnet')
nltk.download('omw-1.4')
# Ensure the SpaCy model is installed
try:
nlp = spacy.load("en_core_web_sm")
except OSError:
subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
nlp = spacy.load("en_core_web_sm")
# 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]
return []
# 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)
# Paraphrasing function using SpaCy and NLTK
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_ in {"NOUN"}:
pos = wordnet.NOUN
elif token.pos_ in {"VERB"}:
pos = wordnet.VERB
elif token.pos_ in {"ADJ"}:
pos = wordnet.ADJ
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 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)
# Join the words back into a sentence
paraphrased_sentence = ' '.join(paraphrased_words)
# Capitalize sentences and proper nouns
corrected_text = capitalize_sentences_and_nouns(paraphrased_sentence)
return corrected_text
# Combined function: Paraphrase -> Capitalization
def paraphrase_and_correct(text):
# Step 1: Paraphrase the text
paraphrased_text = paraphrase_with_spacy_nltk(text)
# Step 2: Capitalize sentences and proper nouns
final_text = capitalize_sentences_and_nouns(paraphrased_text)
return final_text
# Gradio interface for paraphrasing and text correction
with gr.Blocks() as paraphrase_interface:
with gr.Row():
with gr.Column():
text_input = gr.Textbox(lines=5, label="Input Text")
paraphrase_button = gr.Button("Paraphrase & Correct")
with gr.Column():
output_text = gr.Textbox(label="Paraphrased Text")
paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
# Launch the Gradio app for paraphrasing and text correction
paraphrase_interface.launch(debug=False)