语言理解 (LUIS) 中的人工智能Artificial intelligence in Language Understanding (LUIS)

LUIS 根据定义的架构,使用人工智能 (AI) 提供对数据的自然语言理解 (NLU)。LUIS uses artificial intelligence (AI) to provide natural language understanding (NLU) to your data, based on the schema you defined.

自然语言处理 (NLP)Natural language processing (NLP)

自然语言理解 (NLU) 是自然语言处理 (NLP) 的特定子主题。Natural Language Understanding (NLU) is a specific subtopic of Natural Language Processing (NLP).

自然语言处理是一个更广泛的概念,可以用于任何形式的文本数据处理,其中包括:Natural language processing is a broader concept that handles any form of processing of textual data, this includes things like:

  • 词汇切分Tokenization,
  • 词性 (pos) 标记Part of Speech (pos) Tagging
  • 分段Segmentation
  • 语形学分析Morphological analysis
  • 语义相似性Semantic similarity
  • 公开 (Discourse)Discourse
  • 翻译Translation

LUIS 中的自然语言处理Natural language processing in LUIS

可以通过以下方式在 LUIS 应用中使用自然语言处理:Natural language processing is available to your LUIS app in the following ways:

自然语言理解 (NLU)Natural language understanding (NLU)

NLU 功能可用于将口语语句转换为可让你自然地理解用户意思的表示形式。NLU is the ability to transform a linguistic statement to a representation that enables you to understand your users naturally. 自然语言理解仍是一个极具挑战性的问题,被定义为一个 AI 难题。Natural language understanding remains a very challenging problem and is defined as an AI-hard problem.

LUIS 旨在关注意图和提取,这包括能够识别:LUIS is intended to focus on intention and extraction, this includes being able to identify:

  • 用户需求What the user wants
  • 用户谈论的内容。What they are talking about.

在示例中没有明确标识的情况下,LUIS 几乎或完全不了解更广泛的 NLP 特性(例如语义相似性)。LUIS has little or no knowledge of the broader NLP aspects, such as semantic similarity, without explicit identification in examples. 例如,在所提供的示例中将以下标记(单词)用于相似的上下文中之前,它们是三个不同的内容:For example, the following tokens (words) are three different things until they are used in similar contexts in the examples provided:

  • buybuy
  • buyingbuying
  • boughtbought

后续步骤Next steps