Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -7,14 +7,16 @@ import nltk
|
|
7 |
from nltk.corpus import wordnet
|
8 |
from spellchecker import SpellChecker
|
9 |
import re
|
10 |
-
|
11 |
|
12 |
# Initialize the English text classification pipeline for AI detection
|
13 |
pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
|
14 |
|
15 |
-
# Initialize the spell checker
|
16 |
spell = SpellChecker()
|
17 |
-
|
|
|
|
|
18 |
|
19 |
# Ensure necessary NLTK data is downloaded
|
20 |
nltk.download('wordnet')
|
@@ -27,7 +29,7 @@ except OSError:
|
|
27 |
subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
|
28 |
nlp = spacy.load("en_core_web_sm")
|
29 |
|
30 |
-
# Function to predict AI
|
31 |
def predict_en(text):
|
32 |
res = pipeline_en(text)[0]
|
33 |
return res['label'], res['score']
|
@@ -37,66 +39,247 @@ def get_synonyms_nltk(word, pos):
|
|
37 |
synsets = wordnet.synsets(word, pos=pos)
|
38 |
if synsets:
|
39 |
lemmas = synsets[0].lemmas()
|
40 |
-
return [lemma.name() for lemma in lemmas if lemma.name() != word]
|
41 |
return []
|
42 |
|
43 |
-
# Function to remove redundant words
|
44 |
def remove_redundant_words(text):
|
|
|
45 |
meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
|
46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
# Function to correct spelling errors
|
49 |
def correct_spelling(text):
|
50 |
words = text.split()
|
51 |
-
corrected_words = [
|
|
|
|
|
|
|
52 |
return ' '.join(corrected_words)
|
53 |
|
54 |
-
# Function to
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
def rephrase_with_synonyms(text):
|
56 |
doc = nlp(text)
|
57 |
rephrased_text = []
|
58 |
|
59 |
for token in doc:
|
60 |
-
|
61 |
-
"
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
if pos_tag:
|
68 |
synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
|
69 |
-
|
70 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
else:
|
72 |
rephrased_text.append(token.text)
|
73 |
|
74 |
return ' '.join(rephrased_text)
|
75 |
|
76 |
-
# Function to paraphrase and correct grammar
|
77 |
def paraphrase_and_correct(text):
|
|
|
78 |
cleaned_text = remove_redundant_words(text)
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
#
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
)
|
100 |
-
|
101 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
iface.launch()
|
|
|
7 |
from nltk.corpus import wordnet
|
8 |
from spellchecker import SpellChecker
|
9 |
import re
|
10 |
+
import inflect
|
11 |
|
12 |
# Initialize the English text classification pipeline for AI detection
|
13 |
pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
|
14 |
|
15 |
+
# Initialize the spell checker
|
16 |
spell = SpellChecker()
|
17 |
+
|
18 |
+
# Initialize the inflect engine for pluralization
|
19 |
+
inflect_engine = inflect.engine()
|
20 |
|
21 |
# Ensure necessary NLTK data is downloaded
|
22 |
nltk.download('wordnet')
|
|
|
29 |
subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
|
30 |
nlp = spacy.load("en_core_web_sm")
|
31 |
|
32 |
+
# Function to predict the label and score for English text (AI Detection)
|
33 |
def predict_en(text):
|
34 |
res = pipeline_en(text)[0]
|
35 |
return res['label'], res['score']
|
|
|
39 |
synsets = wordnet.synsets(word, pos=pos)
|
40 |
if synsets:
|
41 |
lemmas = synsets[0].lemmas()
|
42 |
+
return [lemma.name() for lemma in lemmas if lemma.name() != word]
|
43 |
return []
|
44 |
|
45 |
+
# Function to remove redundant and meaningless words
|
46 |
def remove_redundant_words(text):
|
47 |
+
doc = nlp(text)
|
48 |
meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
|
49 |
+
filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
|
50 |
+
return ' '.join(filtered_text)
|
51 |
+
|
52 |
+
# Function to capitalize the first letter of sentences and proper nouns
|
53 |
+
def capitalize_sentences_and_nouns(text):
|
54 |
+
doc = nlp(text)
|
55 |
+
corrected_text = []
|
56 |
+
|
57 |
+
for sent in doc.sents:
|
58 |
+
sentence = []
|
59 |
+
for token in sent:
|
60 |
+
if token.i == sent.start: # First word of the sentence
|
61 |
+
sentence.append(token.text.capitalize())
|
62 |
+
elif token.pos_ == "PROPN": # Proper noun
|
63 |
+
sentence.append(token.text.capitalize())
|
64 |
+
else:
|
65 |
+
sentence.append(token.text)
|
66 |
+
corrected_text.append(' '.join(sentence))
|
67 |
+
|
68 |
+
return ' '.join(corrected_text)
|
69 |
+
|
70 |
+
# Function to correct tense errors in a sentence
|
71 |
+
def correct_tense_errors(text):
|
72 |
+
doc = nlp(text)
|
73 |
+
corrected_text = []
|
74 |
+
for token in doc:
|
75 |
+
if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
|
76 |
+
lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
|
77 |
+
corrected_text.append(lemma)
|
78 |
+
else:
|
79 |
+
corrected_text.append(token.text)
|
80 |
+
return ' '.join(corrected_text)
|
81 |
+
|
82 |
+
# Function to correct singular/plural errors
|
83 |
+
def correct_singular_plural_errors(text):
|
84 |
+
doc = nlp(text)
|
85 |
+
corrected_text = []
|
86 |
+
|
87 |
+
for token in doc:
|
88 |
+
if token.pos_ == "NOUN":
|
89 |
+
if token.tag_ == "NN": # Singular noun
|
90 |
+
if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
|
91 |
+
corrected_text.append(inflect_engine.plural(token.lemma_))
|
92 |
+
else:
|
93 |
+
corrected_text.append(token.text)
|
94 |
+
elif token.tag_ == "NNS": # Plural noun
|
95 |
+
if any(child.text.lower() in ['a', 'one'] for child in token.head.children):
|
96 |
+
corrected_text.append(inflect_engine.singular_noun(token.text) or token.text)
|
97 |
+
else:
|
98 |
+
corrected_text.append(token.text)
|
99 |
+
else:
|
100 |
+
corrected_text.append(token.text)
|
101 |
+
|
102 |
+
return ' '.join(corrected_text)
|
103 |
+
|
104 |
+
# Function to check and correct article errors
|
105 |
+
def correct_article_errors(text):
|
106 |
+
doc = nlp(text)
|
107 |
+
corrected_text = []
|
108 |
+
for token in doc:
|
109 |
+
if token.text in ['a', 'an']:
|
110 |
+
next_token = token.nbor(1)
|
111 |
+
if token.text == "a" and next_token.text[0].lower() in "aeiou":
|
112 |
+
corrected_text.append("an")
|
113 |
+
elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
|
114 |
+
corrected_text.append("a")
|
115 |
+
else:
|
116 |
+
corrected_text.append(token.text)
|
117 |
+
else:
|
118 |
+
corrected_text.append(token.text)
|
119 |
+
return ' '.join(corrected_text)
|
120 |
+
|
121 |
+
# Function to get the correct synonym while maintaining verb form
|
122 |
+
def replace_with_synonym(token):
|
123 |
+
pos = None
|
124 |
+
if token.pos_ == "VERB":
|
125 |
+
pos = wordnet.VERB
|
126 |
+
elif token.pos_ == "NOUN":
|
127 |
+
pos = wordnet.NOUN
|
128 |
+
elif token.pos_ == "ADJ":
|
129 |
+
pos = wordnet.ADJ
|
130 |
+
elif token.pos_ == "ADV":
|
131 |
+
pos = wordnet.ADV
|
132 |
+
|
133 |
+
synonyms = get_synonyms_nltk(token.lemma_, pos)
|
134 |
+
|
135 |
+
if synonyms:
|
136 |
+
synonym = synonyms[0]
|
137 |
+
if token.tag_ == "VBG": # Present participle (e.g., running)
|
138 |
+
synonym = synonym + 'ing'
|
139 |
+
elif token.tag_ == "VBD" or token.tag_ == "VBN": # Past tense or past participle
|
140 |
+
synonym = synonym + 'ed'
|
141 |
+
elif token.tag_ == "VBZ": # Third-person singular present
|
142 |
+
synonym = synonym + 's'
|
143 |
+
return synonym
|
144 |
+
return token.text
|
145 |
+
|
146 |
+
# Function to check for and avoid double negatives
|
147 |
+
def correct_double_negatives(text):
|
148 |
+
doc = nlp(text)
|
149 |
+
corrected_text = []
|
150 |
+
for token in doc:
|
151 |
+
if token.text.lower() == "not" and any(child.text.lower() == "never" for child in token.head.children):
|
152 |
+
corrected_text.append("always")
|
153 |
+
else:
|
154 |
+
corrected_text.append(token.text)
|
155 |
+
return ' '.join(corrected_text)
|
156 |
+
|
157 |
+
# Function to ensure subject-verb agreement
|
158 |
+
def ensure_subject_verb_agreement(text):
|
159 |
+
doc = nlp(text)
|
160 |
+
corrected_text = []
|
161 |
+
for token in doc:
|
162 |
+
if token.dep_ == "nsubj" and token.head.pos_ == "VERB":
|
163 |
+
if token.tag_ == "NN" and token.head.tag_ != "VBZ": # Singular noun, should use singular verb
|
164 |
+
corrected_text.append(token.head.lemma_ + "s")
|
165 |
+
elif token.tag_ == "NNS" and token.head.tag_ == "VBZ": # Plural noun, should not use singular verb
|
166 |
+
corrected_text.append(token.head.lemma_)
|
167 |
+
corrected_text.append(token.text)
|
168 |
+
return ' '.join(corrected_text)
|
169 |
|
170 |
# Function to correct spelling errors
|
171 |
def correct_spelling(text):
|
172 |
words = text.split()
|
173 |
+
corrected_words = []
|
174 |
+
for word in words:
|
175 |
+
corrected_word = spell.correction(word)
|
176 |
+
corrected_words.append(corrected_word if corrected_word else word) # Keep original if correction is None
|
177 |
return ' '.join(corrected_words)
|
178 |
|
179 |
+
# Function to correct punctuation issues
|
180 |
+
def correct_punctuation(text):
|
181 |
+
text = re.sub(r'\s+([?.!,";:])', r'\1', text) # Remove space before punctuation
|
182 |
+
text = re.sub(r'([?.!,";:])\s+', r'\1 ', text) # Ensure a single space after punctuation
|
183 |
+
return text
|
184 |
+
|
185 |
+
# Function to ensure correct handling of possessive forms
|
186 |
+
def handle_possessives(text):
|
187 |
+
text = re.sub(r"\b(\w+)'s\b", r"\1's", text) # Preserve possessive forms
|
188 |
+
return text
|
189 |
+
|
190 |
+
# Function to rephrase text and replace words with their synonyms while maintaining form
|
191 |
def rephrase_with_synonyms(text):
|
192 |
doc = nlp(text)
|
193 |
rephrased_text = []
|
194 |
|
195 |
for token in doc:
|
196 |
+
if token.pos_ == "NOUN" and token.text.lower() == "earth":
|
197 |
+
rephrased_text.append("Earth")
|
198 |
+
continue
|
199 |
+
|
200 |
+
pos_tag = None
|
201 |
+
if token.pos_ == "NOUN":
|
202 |
+
pos_tag = wordnet.NOUN
|
203 |
+
elif token.pos_ == "VERB":
|
204 |
+
pos_tag = wordnet.VERB
|
205 |
+
elif token.pos_ == "ADJ":
|
206 |
+
pos_tag = wordnet.ADJ
|
207 |
+
elif token.pos_ == "ADV":
|
208 |
+
pos_tag = wordnet.ADV
|
209 |
|
210 |
if pos_tag:
|
211 |
synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
|
212 |
+
if synonyms:
|
213 |
+
synonym = synonyms[0] # Just using the first synonym for simplicity
|
214 |
+
if token.pos_ == "VERB":
|
215 |
+
if token.tag_ == "VBG": # Present participle (e.g., running)
|
216 |
+
synonym = synonym + 'ing'
|
217 |
+
elif token.tag_ == "VBD" or token.tag_ == "VBN": # Past tense or past participle
|
218 |
+
synonym = synonym + 'ed'
|
219 |
+
elif token.tag_ == "VBZ": # Third-person singular present
|
220 |
+
synonym = synonym + 's'
|
221 |
+
rephrased_text.append(synonym)
|
222 |
+
else:
|
223 |
+
rephrased_text.append(token.text)
|
224 |
else:
|
225 |
rephrased_text.append(token.text)
|
226 |
|
227 |
return ' '.join(rephrased_text)
|
228 |
|
229 |
+
# Function to paraphrase and correct grammar with enhanced accuracy
|
230 |
def paraphrase_and_correct(text):
|
231 |
+
# Remove meaningless or redundant words first
|
232 |
cleaned_text = remove_redundant_words(text)
|
233 |
+
|
234 |
+
# Capitalize sentences and nouns
|
235 |
+
paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
|
236 |
+
|
237 |
+
# Correct tense errors
|
238 |
+
paraphrased_text = correct_tense_errors(paraphrased_text)
|
239 |
+
|
240 |
+
# Correct singular/plural errors
|
241 |
+
paraphrased_text = correct_singular_plural_errors(paraphrased_text)
|
242 |
+
|
243 |
+
# Correct article errors
|
244 |
+
paraphrased_text = correct_article_errors(paraphrased_text)
|
245 |
+
|
246 |
+
# Correct spelling
|
247 |
+
paraphrased_text = correct_spelling(paraphrased_text)
|
248 |
+
|
249 |
+
# Correct punctuation issues
|
250 |
+
paraphrased_text = correct_punctuation(paraphrased_text)
|
251 |
+
|
252 |
+
# Handle possessives
|
253 |
+
paraphrased_text = handle_possessives(paraphrased_text)
|
254 |
+
|
255 |
+
# Replace words with synonyms
|
256 |
+
paraphrased_text = rephrase_with_synonyms(paraphrased_text)
|
257 |
+
|
258 |
+
# Correct double negatives
|
259 |
+
paraphrased_text = correct_double_negatives(paraphrased_text)
|
260 |
+
|
261 |
+
# Ensure subject-verb agreement
|
262 |
+
paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
|
263 |
+
|
264 |
+
return paraphrased_text
|
265 |
+
|
266 |
+
# Function to detect AI-generated content
|
267 |
+
def detect_ai(text):
|
268 |
+
label, score = predict_en(text)
|
269 |
+
return label, score
|
270 |
+
|
271 |
+
# Gradio interface setup
|
272 |
+
def gradio_interface(text):
|
273 |
+
ai_result = detect_ai(text)
|
274 |
+
corrected_text = paraphrase_and_correct(text)
|
275 |
+
return ai_result, corrected_text
|
276 |
+
|
277 |
+
# Create Gradio interface
|
278 |
+
iface = gr.Interface(fn=gradio_interface,
|
279 |
+
inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
|
280 |
+
outputs=[gr.outputs.Label(num_top_classes=2), gr.outputs.Textbox()],
|
281 |
+
title="AI Detection and Grammar Correction",
|
282 |
+
description="Detect AI-generated content and correct grammar issues.")
|
283 |
+
|
284 |
+
# Launch the app
|
285 |
iface.launch()
|