如何将复杂,复合和较长的句子拆分为python中的简单句子

问题描述 投票:-1回答:1

我想将复杂和复合的句子拆分为简单的句子。我想使用一组连接器作为分离器。我尽量不要使用诸如[,]之类的标点符号作为分隔符。我计划使用一组连接器,例如and和or,但as,甚至,尽管,虽然,但作为分离器。例如:

sent='text mining is interesting but it is challenging. I am still learning it as I believe its future application is obvious'.
expected output=['text mining is interesting', 'but it is challenging. I am still learning it', 'as I believe its future application is obvious']

请提供任何帮助。

python split tokenize sentence
1个回答
0
投票

您可以使用OpenNLP(开放自然语言处理)来执行此操作。请参阅this堆栈溢出问题。

© www.soinside.com 2019 - 2024. All rights reserved.