DISAMBIGUATING ASSISTANT TASKS USING SUPPLEMENTAL DATA

A virtual, intelligent, or computational assistant (e.g., also referred to simply as an “assistant”) is described that relies on supplemental data (e.g., contextual information, user information, etc.) to decipher, and determine actions to perform based on, otherwise ambiguous user commands. With explicit permission from a user, the assistant may access a user’s location history, calendar, e-mail, messages, past assistant interactions, contacts, photos, search history, sensor data, and other contextual or user information to interpret user statements. The supplemental data can be stored locally on a device that is executing the assistant or in a cloud computing environment that is accessible to the assistant from the device. This way, the assistant can understand, and perform actions in response to, more complex, compound, and often ambiguous commands even if the commands are generalized, not specific, and/or could be interpreted in different ways, depending on the context or location in which the user provides the command