Patents by Inventor Lingfeng Cheng

Lingfeng Cheng 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: 11990058
    Abstract: An example method embodying the disclosed technology comprises: digitally storing Teacher models and a Student model at a server computer; training each model with a corpus of unlabeled training data using Masked Language Modeling; fine-tuning each Teacher model for an ASAG task with labeled ground truth data; executing each Teacher model to generate and digitally store a respective set of class probabilities on an unlabeled task-specific data set for the ASAG task; further training the Student model by a linear ensemble of the Teacher models using KD; receiving, at the server computer, digital input comprising a target response text and a corresponding target reference answer text; programmatically inputting the target response text and the corresponding target reference answer text to the Student model, thereby outputting a corresponding predicted binary label; displaying correction data indicating the corresponding predicted binary label in a GUI; and, optionally, displaying explainability data in the GUI.
    Type: Grant
    Filed: September 19, 2022
    Date of Patent: May 21, 2024
    Assignee: Quizlet, Inc.
    Inventors: Murali krishna teja Kilari, Shane Curtis Mooney, Lingfeng Cheng
  • Publication number: 20230120965
    Abstract: An example method embodying the disclosed technology comprises: digitally storing Teacher models and a Student model at a server computer; training each model with a corpus of unlabeled training data using Masked Language Modeling; fine-tuning each Teacher model for an ASAG task with labeled ground truth data; executing each Teacher model to generate and digitally store a respective set of class probabilities on an unlabeled task-specific data set for the ASAG task; further training the Student model by a linear ensemble of the Teacher models using KD; receiving, at the server computer, digital input comprising a target response text and a corresponding target reference answer text; programmatically inputting the target response text and the corresponding target reference answer text to the Student model, thereby outputting a corresponding predicted binary label; displaying correction data indicating the corresponding predicted binary label in a GUI; and, optionally, displaying explainability data in the GUI.
    Type: Application
    Filed: September 19, 2022
    Publication date: April 20, 2023
    Inventors: Murali krishna teja Kilari, Shane Curtis Mooney, Lingfeng Cheng
  • Patent number: 11450225
    Abstract: An example method embodying the disclosed technology comprises: digitally storing Teacher models and a Student model at a server computer; training each model with a corpus of unlabeled training data using Masked Language Modeling; fine-tuning each Teacher model for an ASAG task with labeled ground truth data; executing each Teacher model to generate and digitally store a respective set of class probabilities on an unlabeled task-specific data set for the ASAG task; further training the Student model by a linear ensemble of the Teacher models using KD; receiving, at the server computer, digital input comprising a target response text and a corresponding target reference answer text; programmatically inputting the target response text and the corresponding target reference answer text to the Student model, thereby outputting a corresponding predicted binary label; displaying correction data indicating the corresponding predicted binary label in a GUI; and, optionally, displaying explainability data in the GUI.
    Type: Grant
    Filed: October 14, 2021
    Date of Patent: September 20, 2022
    Assignee: QUIZLET, INC.
    Inventors: Murali krishna teja Kilari, Shane Curtis Mooney, Lingfeng Cheng
  • Patent number: 10409866
    Abstract: A method and apparatus for generating normalized occupations for job titles at a job aggregation system is described. The method may include receiving a job title having a plurality of words that make up the job title, the job title received as part of a request of a job aggregation system to perform a service. The method may also include translating the plurality of words into standardized terms of the job aggregation system to generate a translated job title. Furthermore, the method may include mapping the translated job title to one of a plurality of normalized occupations of the job aggregation system by a machine learning based classifier of the translated job title, wherein the machine learning based classifier is trained based on user search behavior of users that have searched for jobs at the job aggregation system.
    Type: Grant
    Filed: June 28, 2016
    Date of Patent: September 10, 2019
    Assignee: GLASSDOOR, INC.
    Inventors: Lingfeng Cheng, Alan Warren Wilson, Vikas Sabnani, Amanda Nichole Baker