Semantic representation using structural ontology for assistant systems

In one embodiment, a method includes receiving, by an assistant xboot, a user input including a natural language utterance from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a tagging syntax for parsing the natural language utterance into semantic units including actions, objects, and attributes, wherein the semantic representation embeds the at least one object into the at least one action and declarates at least one attribute of the embedded object that the action will be taken, sending a request to the agent based on the semantic representation to perform a task corresponding to the user input, a result of the executed task mapped to the fabric determined by the fabric ontology is received from the agent, and an instruction is sent from the assistant xboot to the client system to present a response based on the result of the executed task. 在一个实施例中，一种方法包括由助理xbot从与用户相关联的客户端系统接收包括自然语言话语的用户输入，基于定义用于将自然语言话语解析为包括动作、对象和属性的语义