Digital Genius Limited

Deepmind Technologies Limited

Yoram Bachrach

Samuel John Coope

Bohdan Maksak

Conan McMurtrie

Thore Kurt Hartwig Graepel

Jose Marcos Rodriguez Fernandez

Mahyar Bordbar

Daniel Joseph Strouse

Andrej Zukov Gregorc

Andrej Zukov Gregoric

Andrea Tacchetti

Marta Garnelo Abellanas

Jose Marcos Rodríguez Fernández

Pavel Minkovsky

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for efficiently allocating resources among participants. Methods can include receiving valuation data specifying, for each of a plurality of entities, a respective valuation for each of a plurality of resource subsets, each resource subset comprising a different combination of one or more resources of a plurality of resources. After receiving valuation data, assigning each resource in the plurality of resources to a respective entity of the plurality of entities based on the valuations and generating, for each particular entity, a respective input representation that is derived from valuations of every other entity in the plurality of entities other than the particular entity. The input representation for each particular entity is processed using a neural network to generate a rule for the particular entity and a payment based on the rule output for the entities.

Neural network architecture for efficient resource allocation

A computer-implemented method of tagging a text, comprises: determining a value for each of a plurality of locations in a first vector; processing (), by a trained first neural network component, the first vector to generate a second vector; processing (), at a trained second neural network component, the second vector to generate a probability score for each of at least ten predetermined tags; determining () if each probability score meets a criterion; if the criterion is met, assigning () the tag corresponding to the probability score to the text. Each of the locations may correspond to a respective predetermined word, each value relating to existence and/or frequency of the corresponding word in the text, and the number of locations may be between 600 and 20000. The number of locations in the second vector may be fewer than the number of locations in the first vector and is from 100 to 5000.

Automated tagging of text

Certain examples described herein provide methods and systems for implementing a conversational agent, e.g. to train a predictive model used by the conversational agent. In examples, text data representing agent messages from a dialogue database are clustered and the clusters are used to generate response templates for use by the conversational agent. The predictive model is trained on training data generated by selectively assigning response templates to agent messages from text dialogues. Examples enable a predictive model to be trained on high quality data sets that are generated automatically from a corpus of historical data. In turn, they enable a natural language interface to be efficiently provided.

Conversational agent

Certain examples are described that provide methods and systems for generating templates for use by a conversational agent. These examples enable a natural language interface to be provided. Certain examples cluster user and agent messages from a corpus of text data representing text dialogues. This clustering enables response templates to be generated in a way that takes into account a context in which responses are given. In certain examples, messages that are exchanged between a user and a conversational agent are embedded as numeric arrays based a neural sequence-to-sequence model. Clustering routines are used to group dialogue encodings into one or more response clusters, and these clusters may then be used to generate response templates. The response templates may be used by a conversational agent to prepare a response to a user message.

Template generation for a conversational agent

Growing community of inventors

London, United Kingdom

Yoram Bachrach