tokenizer.texts_to_sequences()
#如果不为不在语料库中的单词创建一个单独的标志,例如"",则可能出现下述情况
当seed_text为"I went to dublin"时,长度为4;当seed_text为"Lawrence went to dublin"时,长度为3,因为Lawrence不再字典中
seed_text = "I went to dublin"
next_words = 2
for _ in range(next_words):
token_list = tokenizer.texts_to_sequences([s
原创
2020-08-01 09:46:43 ·
4734 阅读 ·
0 评论