Patents by Inventor Yi Luan

Yi Luan 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).

  • Systems and methods for determining semantic roles of arguments in sentences
    Patent number: 11164087
    Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive an input sentence including a first predicate and at least a first argument depending from the first predicate, identify the first predicate, identify the first argument based on the first predicate, apply a dependency multiplication to determine a semantic role of the first argument based on the first predicate, and assign the first argument to an argument cluster including one or more similar arguments based on the semantic role of the first argument.
    Type: Grant
    Filed: May 20, 2016
    Date of Patent: November 2, 2021
    Assignee: Disney Enterprises, Inc.
    Inventors: Boyang Li, Yi Luan
  • Systems and Methods for Determining Semantic Roles of Arguments in Sentences
    Publication number: 20170337474
    Abstract: There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive an input sentence including a first predicate and at least a first argument depending from the first predicate, identify the first predicate, identify the first argument based on the first predicate, apply a dependency multiplication to determine a semantic role of the first argument based on the first predicate, and assign the first argument to an argument cluster including one or more similar arguments based on the semantic role of the first argument.
    Type: Application
    Filed: May 20, 2016
    Publication date: November 23, 2017
    Inventors: Boyang Li, Yi Luan
  • Method for using a multi-scale recurrent neural network with pretraining for spoken language understanding tasks
    Patent number: 9607616
    Abstract: A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.
    Type: Grant
    Filed: August 17, 2015
    Date of Patent: March 28, 2017
    Assignee: Mitsubishi Electric Research Laboratories, Inc.
    Inventors: Shinji Watanabe, Yi Luan, Bret Harsham
  • Method for using a Multi-Scale Recurrent Neural Network with Pretraining for Spoken Language Understanding Tasks
    Publication number: 20170053646
    Abstract: A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.
    Type: Application
    Filed: August 17, 2015
    Publication date: February 23, 2017
    Inventors: Shinji Watanabe, Yi Luan, Bret Harsham