Iterative attention-based neural network training and processing

A system, comprising:

• one or more processors;
• one or more memories in communication with the one or more processors;
• and
• one or more programs, wherein the one or more programs are stored in the one or more memories to be executed by the one or more processors, the one or more programs including instructions for causing:
• access to a computer-implemented neural network that is trained, the trained computer-implemented neural network being of a type other than a recurrent neural network;
• access to information including a first plurality of syntactical elements;
• generation, by application of the trained computer-implemented neural network, of a first plurality of probabilities that is associated with the first plurality of syntactical elements;
• a first attention to be directed to a representation of a first subset of the first plurality of syntactical elements based on the first plurality of probabilities, for use by the trained computer-implemented neural network;
• generation, by application of the trained computer-implemented neural network, of a second plurality of probabilities based on the first attention and the first plurality of probabilities generated by the application of the trained computer-implemented neural network;
• a second attention to be directed to a representation of a second subset of the first plurality of syntactical elements based on the second plurality of probabilities, for use by the trained computer-implemented neural network;
• generation, by application of the trained computer-implemented neural network, of a third plurality of probabilities based on the second attention and the second plurality of probabilities generated by the application of the trained computer-implemented neural network;
• generation, by application of the trained computer-implemented neural network, of a second plurality of syntactical elements based on the third plurality of probabilities generated by the application of the trained computer-implemented neural network;
• and
• a communication to be sent to a user.

A system comprising:

• means for accessing a first information comprising a first plurality of syntactical elements;
• means for generating by application of a trained computer-implemented neural network a first plurality of probabilities that are associated with the first plurality of syntactical elements;
• means for directing a first focus of attention of the trained computer-implemented neural network to a representation of a first subset of the first plurality of syntactical elements in accordance with the first plurality of probabilities;
• means for generating a second plurality of probabilities in accordance with the first focus of attention of the trained computer-implemented neural network and the first plurality of probabilities;
• means for directing a second focus of attention of the trained computer-implemented neural network to a representation of a second subset of the first plurality of syntactical elements in accordance with the second plurality of probabilities;
• means for generating a third plurality of probabilities in accordance with the second focus of attention of the trained computer-implemented neural network and the second plurality of probabilities;
• means for generating a second plurality of syntactical elements in accordance with the third plurality of probabilities;
• means for receiving a second information in response to the generated second plurality of syntactical elements;
• and
• means for generating a third plurality of syntactical elements in accordance with the second information.