Abstract: In response to determining that a particular sequence of natural language input has been generated by a first entity participating in a multi-interaction dialog, a first representation of accumulated dialog state associated with the sequence is obtained from a machine learning model at an artificial intelligence service. Based on the first representation, a state response entry is selected from a collection of state response entries. The state response entry indicates a mapping between a second representation of accumulated dialog state, and a response recorded in a training example of the model. The recorded response is implemented.

Abstract: A goal-oriented dialog system interacts with a user over one or more turns of dialog to determine a goal expressed by the user; the dialog system may then act to fulfill the goal by, for example, calling an application-programming interface. The user may supply dialog via text, speech, or other communication. The dialog system includes a first trained model, such as a translation model, to encode the dialog from the user into a context vector; a second trained model, such as another translation model, determines a plurality of candidate probabilities of items in a vocabulary. A language model determines responses to the user based on the input from the user, the context vector, and the plurality of candidate probabilities.

Abstract: Techniques for intelligent task-oriented multi-turn dialog system automation are described. A seq2seq ML model can be trained using a corpus of training data and a loss function that is based at least in part on a distance to a goal. The seq2seq ML model can be provided a user utterance as an input, and a vector of a plurality of values output by a plurality of hidden units of a decoder of the seq2seq ML model can be used to select one or more candidate responses to the user utterance via a nearest neighbor algorithm. In some embodiments, the specially adapted seq2seq ML model can be trained using unsupervised learning, and can be adapted to select intelligent, coherent agent responses that move a task-oriented dialog toward its completion.

Abstract: A system and method for document filtering and selection based on quality automatically operates to make value judgments for document retrieval. Items of data, e.g. documents, are automatically associated a value. Items of data may be then selected based upon value, which is not only for the specific subject or topic requested, but also desirable according to certain criteria, including each document's quality. A specific application of the invention is to a filter for computerized bulletin boards. Many of these systems, also known as discussion groups, have thousands of new messages per day. Readers and human editors do not have time to classify new messages by quality quickly. Messages may be ranked by quality automatically, to perform the same function performed by a human editor or moderator. Values and qualities may be assigned by interestingness, appropriateness, timeliness, humor, style of language, obscenity, sentiment, and any combinations thereof, for example.

Abstract: The present invention relates to a system and method for classifying documents in order to select the most desirable documents of a group. Because quality is very difficult to distinguish by anyone other than a human being, this invention provides a system and method that will create a profile of what constitutes quality, then utilize this profile to allow a user to retrieve information that is desirable. A client is provided with items of data selected according to estimates computed using a profile of certain high-level criteria such as quality, interestingness, appropriateness, timeliness, humor, style of language, obscenity, sentiment, and any combinations thereof. These estimates are computed from low-level criteria such as length, vocabulary, fraction of words spelled correctly, title, author, reading grade level, average length of sentences, average length of words, usage of punctuation, usage of grammar, formatting, capitalization, source, display tags and any combinations thereof.