Google Inc.

Deepmind Technologies Limited

Karol Piotr Kurach

Gregory Sean Corrado

Ilya Sutskever

Balint Miklos

László Lukács

Phillip Neal Sharp

Prabhakar Raghavan

Thompson Alexander Ivor Gawley

Tobias Kaufmann

Andrew M Dai

Peter Junteng Liu

Itamar Gilad

Ivo Krka

Marcin Andrychowicz

Liam MacDermed

Alexandru Damian

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in “reply” messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Determining reply content for a reply to an electronic communication

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in 'reply' messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Systems, methods, devices, and other techniques are disclosed for using an augmented neural network system to generate a sequence of outputs from a sequence of inputs. An augmented neural network system can include a controller neural network, a hierarchical external memory, and a memory access subsystem. The controller neural network receives a neural network input at each of a series of time steps processes the neural network input to generate a memory key for the time step. The external memory includes a set of memory nodes arranged as a binary tree. To provide an interface between the controller neural network and the external memory, the system includes a memory access subsystem that is configured to, for each of the series of time steps, perform one or more operations to generate a respective output for the time step. The capacity of the neural network system to account for long-range dependencies in input sequences may be extended. Also, memory access efficiency may be increased by structuring the external memory as a binary tree.

Augmenting neural networks with hierarchical external memory

Systems and methods for classifying messages are provided. Each message in a plurality of messages is classified, thereby independently identifying a message category in a set of message categories for each respective message in the plurality. The plurality of messages is delivered to a plurality of recipients with a designation of the message category of each respective message in the first plurality of messages. A plurality of recipient initiated message interaction events for messages in the first plurality of messages over a predetermined period of time is collected from the plurality of recipients. A message categorization dataset is then constructed from (i) the first plurality of messages, (ii) the designation of the message category of each respective message in the subset of the first plurality of messages, and (iii) the plurality of recipient initiated message interaction events. This message categorization dataset is used to train or evaluate a message classifier.

Systems and methods for generating a message topic training dataset from user interactions in message clients

Systems and methods for classifying messages are provided. Each message in a plurality of messages is classified, thereby independently identifying a message category in a set of message categories for each respective message in the plurality of messages. The plurality of messages is delivered to a plurality of recipients with a designation of the message category of each respective message in the first plurality of messages. A plurality of recipient initiated message interaction events for messages in the first plurality of messages over a predetermined period of time is collected from the plurality of recipients. A message categorization dataset is then constructed from (i) the first plurality of messages, (ii) the designation of the message category of each respective message in the subset of the first plurality of messages, and (iii) the plurality of recipient initiated message interaction events. This message categorization dataset is used to train or evaluate a message classifier.

Systems and methods are provided for organizing messages. A plurality of messages is communicated to a user with a designation of the message category of each respective message in the plurality of messages. The plurality of messages includes, for each respective message category in a plurality of message categories, at least one message in the respective message category. A user selection of a first message in the plurality of messages is received, whereupon a subset of the plurality of messages similar to the first message is selected based upon respective comparisons of continuous vector representations of (i) a set of words in the first message and (ii) a corresponding set of words in messages in the subset of messages. An identification of each respective message in the subset of messages is then displayed.

Growing community of inventors

Zurich, Switzerland

Karol Piotr Kurach