File size: 3,273 Bytes
84669bc
7feda08
6ba2176
7fc55d1
 
8e09e8c
7fc55d1
 
 
6ba2176
031a20c
6ba2176
 
 
 
 
7feda08
5065a5b
 
 
 
 
 
 
 
3c39506
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f0ffd9
5065a5b
 
 
 
 
6f0ffd9
5065a5b
 
 
 
 
 
 
 
 
 
 
 
73ae45e
5065a5b
 
 
 
 
73ae45e
5065a5b
73ae45e
3c39506
 
5065a5b
73ae45e
5065a5b
d3c4b21
41941cd
 
 
 
ddf9006
d3c4b21
41941cd
 
 
5cbdb52
 
5065a5b
 
aec8023
 
 
5cbdb52
5065a5b
5cbdb52
aed9390
5cbdb52
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
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)