Spaces:
Running
Running
File size: 24,617 Bytes
b265c4f 3a1a87f b265c4f 3a1a87f b265c4f 38620f7 b265c4f be52172 b265c4f be52172 b265c4f be52172 3a1a87f be52172 3a1a87f be52172 3a1a87f be52172 3a1a87f be52172 3a1a87f be52172 3a1a87f b265c4f ef90cef be52172 38620f7 9e1613b 38620f7 be52172 9e1613b 38620f7 9e1613b 38620f7 9e1613b 38620f7 9e1613b 38620f7 a4dbf67 38620f7 a4dbf67 be52172 b265c4f be52172 b265c4f be52172 b265c4f ef90cef be52172 38620f7 ef90cef b265c4f 3a1a87f ef90cef 3a1a87f be52172 3a1a87f be52172 a4dbf67 38620f7 3a1a87f a4dbf67 be52172 a4dbf67 b265c4f be52172 a4dbf67 b265c4f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 |
# -*- coding: utf-8 -*-
"""text-paraphraser.ipynb
Automatically generated by Colab.
Original file is located at
https://colab.research.google.com/drive/1pFGR4uvXMMWVJFQeFmn--arumSxqa5Yy
"""
from transformers import AutoTokenizer
from transformers import AutoModelForSeq2SeqLM
import plotly.graph_objs as go
import textwrap
from transformers import pipeline
import re
import time
import requests
from PIL import Image
import itertools
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
from matplotlib.colors import ListedColormap, rgb2hex
import ipywidgets as widgets
from IPython.display import display, HTML
import pandas as pd
from pprint import pprint
from tenacity import retry
from tqdm import tqdm
# import tiktoken
import scipy.stats
import torch
from transformers import GPT2LMHeadModel
import seaborn as sns
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForMaskedLM
# from colorama import Fore, Style
# import openai
import random
from nltk.corpus import stopwords
from termcolor import colored
import nltk
from nltk.translate.bleu_score import sentence_bleu
from transformers import BertTokenizer, BertModel
import graphviz
import gradio as gr
nltk.download('stopwords')
# Function to Initialize the Model
def init_model():
para_tokenizer = AutoTokenizer.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base")
para_model = AutoModelForSeq2SeqLM.from_pretrained("humarin/chatgpt_paraphraser_on_T5_base")
return para_tokenizer, para_model
# Function to Paraphrase the Text
def paraphrase(question, para_tokenizer, para_model, num_beams=5, num_beam_groups=5, num_return_sequences=5, repetition_penalty=10.0, diversity_penalty=3.0, no_repeat_ngram_size=2, temperature=0.7, max_length=64):
input_ids = para_tokenizer(
f'paraphrase: {question}',
return_tensors="pt", padding="longest",
max_length=max_length,
truncation=True,
).input_ids
outputs = para_model.generate(
input_ids, temperature=temperature, repetition_penalty=repetition_penalty,
num_return_sequences=num_return_sequences, no_repeat_ngram_size=no_repeat_ngram_size,
num_beams=num_beams, num_beam_groups=num_beam_groups,
max_length=max_length, diversity_penalty=diversity_penalty
)
res = para_tokenizer.batch_decode(outputs, skip_special_tokens=True)
return res
# Function to Find the Longest Common Substring Words Subsequence
def longest_common_subss(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for sentence in paraphrased_sentences_no_stopwords:
common_words = set(original_sentence_lower.split()) & set(sentence.split())
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
"Original Sentence": original_sentence_lower,
"Paraphrased Sentence": sentence,
"Substrings Word Pair": common_words
})
return results
# Function to Find Common Substring Word between each paraphrase sentences
def common_substring_word(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for idx, sentence in enumerate(paraphrased_sentences_no_stopwords):
common_words = set(original_sentence_lower.split()) & set(sentence.split())
common_substrings = ', '.join(sorted(common_words))
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
f"Paraphrased Sentence {idx+1}": sentence,
"Common Substrings": common_substrings
})
return results
# Function to Watermark a Word Take Randomly Between Each lcs Point (Random Sampling)
def random_sampling(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for idx, sentence in enumerate(paraphrased_sentences_no_stopwords):
common_words = set(original_sentence_lower.split()) & set(sentence.split())
common_substrings = ', '.join(sorted(common_words))
words_to_replace = [word for word in sentence.split() if word not in common_words]
if words_to_replace:
word_to_mark = random.choice(words_to_replace)
sentence = sentence.replace(word_to_mark, colored(word_to_mark, 'red'))
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
f"Paraphrased Sentence {idx+1}": sentence,
"Common Substrings": common_substrings
})
return results
# Function for Inverse Transform Sampling
def inverse_transform_sampling(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for idx, sentence in enumerate(paraphrased_sentences_no_stopwords):
common_words = set(original_sentence_lower.split()) & set(sentence.split())
common_substrings = ', '.join(sorted(common_words))
words_to_replace = [word for word in sentence.split() if word not in common_words]
if words_to_replace:
probabilities = [1 / len(words_to_replace)] * len(words_to_replace)
chosen_word = random.choices(words_to_replace, weights=probabilities)[0]
sentence = sentence.replace(chosen_word, colored(chosen_word, 'magenta'))
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
f"Paraphrased Sentence {idx+1}": sentence,
"Common Substrings": common_substrings
})
return results
# Function for Contextual Sampling
def contextual_sampling(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for idx, sentence in enumerate(paraphrased_sentences_no_stopwords):
common_words = set(original_sentence_lower.split()) & set(sentence.split())
common_substrings = ', '.join(sorted(common_words))
words_to_replace = [word for word in sentence.split() if word not in common_words]
if words_to_replace:
context = " ".join([word for word in sentence.split() if word not in common_words])
chosen_word = random.choice(words_to_replace)
sentence = sentence.replace(chosen_word, colored(chosen_word, 'red'))
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
f"Paraphrased Sentence {idx+1}": sentence,
"Common Substrings": common_substrings
})
return results
# Function for Exponential Minimum Sampling
def exponential_minimum_sampling(original_sentence, paraphrased_sentences):
stop_words = set(stopwords.words('english'))
original_sentence_lower = original_sentence.lower()
paraphrased_sentences_lower = [s.lower() for s in paraphrased_sentences]
paraphrased_sentences_no_stopwords = []
for sentence in paraphrased_sentences_lower:
words = re.findall(r'\b\w+\b', sentence)
filtered_sentence = ' '.join([word for word in words if word not in stop_words])
paraphrased_sentences_no_stopwords.append(filtered_sentence)
results = []
for idx, sentence in enumerate(paraphrased_sentences_no_stopwords):
common_words = set(original_sentence_lower.split()) & set(sentence.split())
common_substrings = ', '.join(sorted(common_words))
words_to_replace = [word for word in sentence.split() if word not in common_words]
if words_to_replace:
num_words = len(words_to_replace)
probabilities = [2 ** (-i) for i in range(num_words)]
chosen_word = random.choices(words_to_replace, weights=probabilities)[0]
sentence = sentence.replace(chosen_word, colored(chosen_word, 'red'))
for word in common_words:
sentence = sentence.replace(word, colored(word, 'green'))
results.append({
f"Paraphrased Sentence {idx+1}": sentence,
"Common Substrings": common_substrings
})
return results
# Function to Calculate the BLEU score
def calculate_bleu(reference, candidate):
return sentence_bleu([reference], candidate)
# Function to calculate BERT score
def calculate_bert(reference, candidate):
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')
reference_tokens = tokenizer.tokenize(reference)
candidate_tokens = tokenizer.tokenize(candidate)
reference_ids = tokenizer.encode(reference, add_special_tokens=True, max_length=512, truncation=True, return_tensors="pt")
candidate_ids = tokenizer.encode(candidate, add_special_tokens=True, max_length=512, truncation=True, return_tensors="pt")
with torch.no_grad():
reference_outputs = model(reference_ids)
candidate_outputs = model(candidate_ids)
reference_embeddings = reference_outputs[0][:, 0, :].numpy()
candidate_embeddings = candidate_outputs[0][:, 0, :].numpy()
cosine_similarity = np.dot(reference_embeddings, candidate_embeddings.T) / (np.linalg.norm(reference_embeddings) * np.linalg.norm(candidate_embeddings))
return np.mean(cosine_similarity)
# Function to calculate minimum edit distance
def min_edit_distance(reference, candidate):
m = len(reference)
n = len(candidate)
dp = [[0] * (n + 1) for _ in range(m + 1)]
for i in range(m + 1):
for j in range(n + 1):
if i == 0:
dp[i][j] = j
elif j == 0:
dp[i][j] = i
elif reference[i - 1] == candidate[j - 1]:
dp[i][j] = dp[i - 1][j - 1]
else:
dp[i][j] = 1 + min(dp[i][j - 1], # Insert
dp[i - 1][j], # Remove
dp[i - 1][j - 1]) # Replace
return dp[m][n]
def generate_paraphrase(question):
para_tokenizer, para_model = init_model()
res = paraphrase(question, para_tokenizer, para_model)
return res
question = "Following the declaration of the State of Israel in 1948, neighboring Arab states invaded. The war ended with Israel controlling a significant portion of the territory. Many Palestinians became refugees."
import re
from nltk.corpus import stopwords
def find_common_subsequences(sentence, str_list):
stop_words = set(stopwords.words('english'))
sentence = sentence.lower()
str_list = [s.lower() for s in str_list]
def is_present(lcs, str_list):
for string in str_list:
if lcs not in string:
return False
return True
def remove_stop_words_and_special_chars(sentence):
sentence = re.sub(r'[^\w\s]', '', sentence)
words = sentence.split()
filtered_words = [word for word in words if word.lower() not in stop_words]
return " ".join(filtered_words)
sentence = remove_stop_words_and_special_chars(sentence)
str_list = [remove_stop_words_and_special_chars(s) for s in str_list]
words = sentence.split(" ")
common_grams = []
added_phrases = set()
def is_covered(subseq, added_phrases):
for phrase in added_phrases:
if subseq in phrase:
return True
return False
for i in range(len(words) - 4):
penta = " ".join(words[i:i+5])
if is_present(penta, str_list):
common_grams.append(penta)
added_phrases.add(penta)
for i in range(len(words) - 3):
quad = " ".join(words[i:i+4])
if is_present(quad, str_list) and not is_covered(quad, added_phrases):
common_grams.append(quad)
added_phrases.add(quad)
for i in range(len(words) - 2):
tri = " ".join(words[i:i+3])
if is_present(tri, str_list) and not is_covered(tri, added_phrases):
common_grams.append(tri)
added_phrases.add(tri)
for i in range(len(words) - 1):
bi = " ".join(words[i:i+2])
if is_present(bi, str_list) and not is_covered(bi, added_phrases):
common_grams.append(bi)
added_phrases.add(bi)
for i in range(len(words)):
uni = words[i]
if is_present(uni, str_list) and not is_covered(uni, added_phrases):
common_grams.append(uni)
added_phrases.add(uni)
return common_grams
def llm_output(prompt):
return prompt, prompt
def highlight_phrases_with_colors(sentences, phrases):
color_map = {}
color_index = 0
highlighted_html = []
idx = 1
for sentence in sentences:
sentence_with_idx = f"{idx}. {sentence}"
idx += 1
highlighted_sentence = sentence_with_idx
phrase_count = 0
words = re.findall(r'\b\w+\b', sentence)
word_index = 1
for phrase in phrases:
if phrase not in color_map:
color_map[phrase] = f'hsl({color_index * 60 % 360}, 70%, 80%)'
color_index += 1
escaped_phrase = re.escape(phrase)
pattern = rf'\b{escaped_phrase}\b'
highlighted_sentence, num_replacements = re.subn(
pattern,
lambda m, count=phrase_count, color=color_map[phrase], index=word_index: (
f'<span style="background-color: {color}; font-weight: bold;'
f' padding: 2px 4px; border-radius: 2px; position: relative;">'
f'<span style="background-color: black; color: white; border-radius: 50%;'
f' padding: 2px 5px; margin-right: 5px;">{index}</span>'
f'{m.group(0)}'
f'</span>'
),
highlighted_sentence,
flags=re.IGNORECASE
)
if num_replacements > 0:
phrase_count += 1
word_index += 1
highlighted_html.append(highlighted_sentence)
final_html = "<br><br>".join(highlighted_html)
return f'''
<div style="border: solid 1px #; padding: 16px; background-color: #FFFFFF; color: #374151; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); border-radius: 2px;">
<h3 style="margin-top: 0; font-size: 1em; color: #111827;">Paraphrased And Highlighted Text</h3>
<div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 2px;">{final_html}</div>
</div>
'''
import re
def highlight_phrases_with_colors_single_sentence(sentence, phrases):
color_map = {}
color_index = 0
highlighted_sentence = sentence
phrase_count = 0
words = re.findall(r'\b\w+\b', sentence)
word_index = 1
for phrase in phrases:
if phrase not in color_map:
color_map[phrase] = f'hsl({color_index * 60 % 360}, 70%, 80%)'
color_index += 1
escaped_phrase = re.escape(phrase)
pattern = rf'\b{escaped_phrase}\b'
highlighted_sentence, num_replacements = re.subn(
pattern,
lambda m, count=phrase_count, color=color_map[phrase], index=word_index: (
f'<span style="background-color: {color}; font-weight: bold;'
f' padding: 2px 4px; border-radius: 2px; position: relative;">'
f'<span style="background-color: black; color: white; border-radius: 50%;'
f' padding: 2px 5px; margin-right: 5px;">{index}</span>'
f'{m.group(0)}'
f'</span>'
),
highlighted_sentence,
flags=re.IGNORECASE
)
if num_replacements > 0:
phrase_count += 1
word_index += 1
final_html = highlighted_sentence
return f'''
<div style="border: solid 1px #; padding: 16px; background-color: #FFFFFF; color: #374151; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); border-radius: 2px;">
<h3 style="margin-top: 0; font-size: 1em; color: #111827;">Selected Sentence</h3>
<div style="background-color: #F5F5F5; line-height: 1.6; padding: 15px; border-radius: 2px;">{final_html}</div>
</div>
'''
# Masking Model
def mask_non_stopword(sentence):
stop_words = set(stopwords.words('english'))
words = sentence.split()
non_stop_words = [word for word in words if word.lower() not in stop_words]
if not non_stop_words:
return sentence
word_to_mask = random.choice(non_stop_words)
masked_sentence = sentence.replace(word_to_mask, '[MASK]', 1)
return masked_sentence
# Load tokenizer and model for masked language model
tokenizer = AutoTokenizer.from_pretrained("bert-large-cased-whole-word-masking")
model = AutoModelForMaskedLM.from_pretrained("bert-large-cased-whole-word-masking")
fill_mask = pipeline("fill-mask", model=model, tokenizer=tokenizer)
def mask(sentence):
predictions = fill_mask(sentence)
masked_sentences = [predictions[i]['sequence'] for i in range(len(predictions))]
return masked_sentences
#plotly tree
import plotly.graph_objs as go
import textwrap
import re
from collections import defaultdict
def generate_plot(original_sentence):
paraphrased_sentences = generate_paraphrase(original_sentence)
first_paraphrased_sentence = paraphrased_sentences[0]
masked_sentence = mask_non_stopword(first_paraphrased_sentence)
masked_versions = mask(masked_sentence)
nodes = []
nodes.append(original_sentence)
nodes.extend(paraphrased_sentences)
nodes.extend(masked_versions)
nodes[0] += ' L0'
para_len = len(paraphrased_sentences)
for i in range(1, para_len+1):
nodes[i] += ' L1'
for i in range(para_len+1, len(nodes)):
nodes[i] += ' L2'
cleaned_nodes = [re.sub(r'\sL[0-9]$', '', node) for node in nodes]
wrapped_nodes = ['<br>'.join(textwrap.wrap(node, width=30)) for node in cleaned_nodes]
def get_levels_and_edges(nodes):
levels = {}
edges = []
for i, node in enumerate(nodes):
level = int(node.split()[-1][1])
levels[i] = level
# Add edges from L0 to all L1 nodes
root_node = next(i for i, level in levels.items() if level == 0)
for i, level in levels.items():
if level == 1:
edges.append((root_node, i))
# Identify the first L1 node
first_l1_node = next(i for i, level in levels.items() if level == 1)
# Add edges from the first L1 node to all L2 nodes
for i, level in levels.items():
if level == 2:
edges.append((first_l1_node, i))
return levels, edges
# Get levels and dynamic edges
levels, edges = get_levels_and_edges(nodes)
max_level = max(levels.values())
# Calculate positions
positions = {}
level_widths = defaultdict(int)
for node, level in levels.items():
level_widths[level] += 1
x_offsets = {level: - (width - 1) / 2 for level, width in level_widths.items()}
y_gap = 4
for node, level in levels.items():
positions[node] = (x_offsets[level], -level * y_gap)
x_offsets[level] += 1
# Create figure
fig = go.Figure()
# Add nodes to the figure
for i, node in enumerate(wrapped_nodes):
x, y = positions[i]
fig.add_trace(go.Scatter(
x=[x],
y=[y],
mode='markers',
marker=dict(size=10, color='blue'),
hoverinfo='none'
))
fig.add_annotation(
x=x,
y=y,
text=node,
showarrow=False,
yshift=20, # Adjust the y-shift value to avoid overlap
align="center",
font=dict(size=10),
bordercolor='black',
borderwidth=1,
borderpad=4,
bgcolor='white',
width=200
)
# Add edges to the figure
for edge in edges:
x0, y0 = positions[edge[0]]
x1, y1 = positions[edge[1]]
fig.add_trace(go.Scatter(
x=[x0, x1],
y=[y0, y1],
mode='lines',
line=dict(color='black', width=2)
))
fig.update_layout(
showlegend=False,
margin=dict(t=50, b=50, l=50, r=50),
xaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
yaxis=dict(showgrid=False, zeroline=False, showticklabels=False),
width=1470,
height=800 # Increase height to provide more space
)
return masked_sentence, masked_versions, fig
# Function for the Gradio interface
def model(prompt):
generated, sentence = llm_output(prompt)
res = generate_paraphrase(sentence)
common_subs = longest_common_subss(sentence, res)
common_grams = find_common_subsequences(sentence, res)
for i in range(len(common_subs)):
common_subs[i]["Paraphrased Sentence"] = res[i]
generated_highlighted = highlight_phrases_with_colors_single_sentence(generated, common_grams)
result = highlight_phrases_with_colors(res, common_grams)
masked_sentence, masked_versions, tree = generate_plot(sentence)
return generated, generated_highlighted, result, masked_sentence, masked_versions, tree
with gr.Blocks(theme = gr.themes.Monochrome()) as demo:
gr.Markdown("# Paraphrases the Text and Highlights the Non-melting Points")
with gr.Row():
user_input = gr.Textbox(label="User Prompt")
with gr.Row():
submit_button = gr.Button("Submit")
clear_button = gr.Button("Clear")
with gr.Row():
ai_output = gr.Textbox(label="AI-generated Text (Llama3)")
with gr.Row():
selected_sentence = gr.HTML()
with gr.Row():
html_output = gr.HTML()
with gr.Row():
masked_sentence = gr.Textbox(label="Masked Sentence")
with gr.Row():
masked_versions = gr.Textbox(label="Sentence Generated by Masking Model")
with gr.Row():
tree = gr.Plot()
submit_button.click(model, inputs=user_input, outputs=[ai_output, selected_sentence, html_output, masked_sentence, masked_versions, tree])
clear_button.click(lambda: "", inputs=None, outputs=user_input)
clear_button.click(lambda: "", inputs=None, outputs=[ai_output, selected_sentence, html_output, masked_sentence, masked_versions, tree])
# Launch the demo
demo.launch(share=True)
|