Patents by Inventor Charles Elkan

Charles Elkan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10963819
    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.
    Type: Grant
    Filed: September 27, 2017
    Date of Patent: March 30, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Rashmi Gangadharaiah, Charles Elkan, Balakrishnan Narayanaswamy
  • Patent number: 10860629
    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.
    Type: Grant
    Filed: April 2, 2018
    Date of Patent: December 8, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan
  • Patent number: 7200606
    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.
    Type: Grant
    Filed: November 2, 2001
    Date of Patent: April 3, 2007
    Assignee: The Regents of the University of California
    Inventor: Charles Elkan
  • Publication number: 20020055940
    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.
    Type: Application
    Filed: November 2, 2001
    Publication date: May 9, 2002
    Inventor: Charles Elkan