At least one non-transitory computer-readable medium having instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following activities: a natural-language input from a user as part of an ongoing human-computer conversation between the user and an automated assistant operated by one or more processors; select one or more grammars to parse the natural language input, wherein the selecting is based on one or more topics stored in memory as part of a contextual data structure associated with the current human computer dialog; parse the natural language input based on the selected one or more grammars to generate one or more parses; generate a natural language response based on one or more of the parses; output the natural language response to the user using one or more output devices; identify one or more topics raised by one or more of the parsys or the natural language answer; and add the identified one or more topics to the contextual data structure.
展开▼