def synonym_replacement(words, n, key_words):
"""
同义词替换,替换一个语句中的n个单词为其同义词
:param words: list, inupt sentence
:param n: int, replace words
:return: list, new_words
"""
new_words = words.copy()
random_word_list = list(
set([word for word in words if word not in stop_words]))
random.shuffle(random_word_list)
num_replaced = 0
for random_word in random_word_list:
sim_synonyms = get_syn_by_synonyms(random_word)
if len(
sim_synonyms
) >= 1 and random_word not in key_words and not is_total_english(
random_word) and not is_total_number(random_word):
synonym = random.choice(sim_synonyms)
new_words = [
synonym if word == random_word else word for word in new_words
]
num_replaced += 1
if num_replaced >= n:
break
sentence = ' '.join(new_words)
new_words = sentence.split(' ')
return new_words
def add_word(new_words, key_words):
"""
在list上随机插入一个同义词
:param words: list, inupt sentence
:return: list, new_words
"""
synonyms = []
counter = 0
while len(synonyms) < 1:
random_word = new_words[random.randint(0, len(new_words) - 1)]
# 过滤
if random_word not in key_words and not is_total_english(random_word) and not is_total_number(random_word):
synonyms = get_syn_by_synonyms(random_word)
counter += 1
if counter >= 10:
return
random_synonym = random.choice(synonyms)
random_idx = random.randint(0, len(new_words) - 1)
new_words.insert(random_idx, random_synonym)
def get_syn_by_synonyms(word):
if not is_total_english(word.strip()):
return synonyms.nearby(word)[0]
else:
return word
