Apple Inc.

Thomas Benedict Gunter

Eric Gregory

Gennaro Frazzingaro

Blaise Thomson

Thorvaldur Pall Helgason

Silvia Frias Delgado

Thomas David Voice

Stephen J Young

Diarmuid Ó Śeaghdha

Dain Kaplan

Keith Scott Brisson

David J Vandyke

Thomas Robert Nickson

Arthur A Van Hoff

Systems and processes for creating and updating natural language models are provided. An example process of creating a natural language model includes, at an electronic device with one or more processors and memory, receiving an utterance, associating an action structure with the utterance, determining a plurality of augmented utterances based on the received utterance, creating a natural language model including the received utterance and the plurality of augmented utterances by mapping the plurality of augmented utterance to the associated action structure, and providing the natural language model including the received utterance and the plurality of augmented utterances to a second electronic device.

Using augmentation to create natural language models

Systems and processes for optimizing dialogue policy decisions for digital assistants using implicit feedback are provided. In an example process, a user utterance is received. Based on a text representation of the user utterance, one or more user intents corresponding to the user utterance are determined. A policy action is selected from a plurality of candidate policy actions based on a belief state for the one or more user intents and a policy model. The policy action is performed, including outputting results of the policy action for presentation. A success score for the policy action is determined based on whether one or more predetermined types of implicit user feedback are detected after performing the policy action. A set of parameter values of the policy model is modified using the determined success score.

Optimizing dialogue policy decisions for digital assistants using implicit feedback

Growing community of inventors

Oxford, United Kingdom

Thomas Benedict Gunter