1. 引言
自然语言理解是人工智能的核心难题之一,也是目前智能语音交互和人机对话的核心难题。维基百科有如下描述[1]:
Natural language understanding (NLU) is a subtopic of natural language processing in artificial intelligence that deals with machine reading comprehension. NLU is considered an AI-hard problem.
对于AI-hard的解释如下:
In the field of artificial intelligence, the most difficult problems are informally known as AI-complete or AI-hard, implying that the difficulty of these computational problems is equivalent to that of solving the central artificial intelligence problem—making computers as intelligent as people, or strong AI.
简言之,什么时候自然语言能被机器很好的理解了,strong AI也就实现了~~
之前写过一篇文章自然语言理解,介绍了当时NLU的系统实现方案,感兴趣的可以再翻一番,里面介绍过的一些内容不再赘述。那篇文章写于2015年底,过去一年多,技术进展非常快,我们的算法也进行了大量升级,核心模块全部升级到深度学习方案。本文主要结合NUI平台中自然语言理解的具体实现,详细的、系统的介绍意图分类和属性抽取两个核心算法。如下图所示,第一个框中是意图分类,第二个框中是属性抽取。