Patents by Inventor Srinivas Ravishankar

Srinivas Ravishankar 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).

  • SEMANTICALLY PARSED KNOWLEDGE BASE QUESTION ANSWERING GENERALIZATION
    Publication number: 20240078443
    Abstract: One or more computer processors improve knowledge base question answering (KBQA) model convergence and prediction performance by generalizing the KBQA model based on transfer learning.
    Type: Application
    Filed: September 7, 2022
    Publication date: March 7, 2024
    Inventors: Srinivas Ravishankar, Dung Ngoc Thai, IBRAHIM ABDELAZIZ, Pavan Kapanipathi Bangalore, TAHIRA NASEEM, Achille Belly Fokoue-Nkoutche, NANDANA MIHINDUKULASOORIYA
  • Knowledge base question answering
    Patent number: 11868716
    Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.
    Type: Grant
    Filed: August 31, 2021
    Date of Patent: January 9, 2024
    Assignee: International Business Machines Corporation
    Inventors: Srinivas Ravishankar, Pavan Kapanipathi Bangalore, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Dinesh Garg, Salim Roukos, Alexander Gray
  • KNOWLEDGE BASE QUESTION ANSWERING
    Publication number: 20230060589
    Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.
    Type: Application
    Filed: August 31, 2021
    Publication date: March 2, 2023
    Inventors: Srinivas Ravishankar, Pavan Kapanipathi Bangalore, IBRAHIM ABDELAZIZ, NANDANA MIHINDUKULASOORIYA, Dinesh Garg, Salim Roukos, Alexander Gray