Google Inc.

Pranav Khaitan

Quoc V Le

Anton Volkov

Sergey Nazarov

Ori Gershony

Dennis A Kiilerich

Ricardo Escutia

Gang Ji

Timothy Seeds Milligan

Cong Li

Jay K Adams

Mei Chen

Manas Rajendra Joglekar

Sushant Prakash

Hila Shemer

David Citron

Shobha Diwakar

Matthew Nirvan Sharifi

David Petrou

Raghav Gupta

Abhinav Kumar Rastogi

Xiaoxue Zang

Srinivas Kumar Sunkara

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

Learning to select vocabularies for categorical features

Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.

Schema-guided response generation

A system and method for identifying an entity from a message exchange thread and generating a suggestion that is directed to the entity, such as a suggestion for a user to take an action on the entity. A suggestion application receives at least one electronic message from a message exchange thread, identifies an entity that can be actionable from the electronic message, determines contextual indicators of the entity, determines whether the entity is actionable based on the contextual indicators, and responsive to the entity being actionable, provides a suggestion that is directed to the entity to a participant(s) of the message exchange thread.

Automatic suggestions for message exchange threads

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving user-specific content, the user-specific content being associated with a user of one or more computer-implemented services, processing the user-specific content using one or more parsers to identify one or more entities and one or more relationships between entities, a parser being specific to a schema, and the one or more entities and the one or more relationships between entities being identified based on the schema, providing one or more user-specific knowledge graphs, a user-specific knowledge graph being specific to the user and including nodes and edges between nodes to define relationships between entities based on the schema, and storing the one or more user-specific knowledge graphs.

Structured user graph to support querying and predictions

Systems and methods are provided for a personal entity modeling for computing devices. For example, a computing device comprises at least one processor and memory storing instructions that, when executed by the at least one processor, cause the mobile device to perform operations including identifying a personal entity in content generated for display on the mobile device, generating training examples for the personal entity from the content, and updating an embedding used to model the personal entity using the training examples. The embedding may be used to make predictions regarding the personal entity. For example, the operations may also include predicting an association between a first personal entity displayed on the computing device and a second entity based on the embedding, and providing a recommendation, to be displayed on the computing device, related to the second entity.

Modeling personal entities on a mobile device using embeddings

A system for providing a trusted peer-based information verification system may include one or more processors and a memory. The one or more processors may facilitate steps of receiving an identification item from a server hosting a web site and providing a request for verification of the identification item to devices of trusted peers. The steps may further include receiving verification responses from the devices of the trusted peers. The verification responses may be indicative of whether identification items received by the devices of the trusted peers via the web site are different than the identification item received from the server hosting the web site. The steps may further include determining a validity of the identification item based on the verification responses received from the devices of the trusted peers. In one example the identification item may be a digital certificate, such as a public key certificate.

Trusted peer-based information verification system

Growing community of inventors

Mountain View, CA, United States of America

Pranav Khaitan