Patents by Inventor Avinash Balakrishnan

Avinash Balakrishnan 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).

  • Model agnostic contrastive explanations for structured data
    Patent number: 11507787
    Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.
    Type: Grant
    Filed: December 12, 2018
    Date of Patent: November 22, 2022
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Amit Dhurandhar, Pin-Yu Chen, Karthikeyan Shanmugam, Tejaswini Pedapati, Avinash Balakrishnan, Ruchir Puri
  • Infusing knowledge into natural language processing tasks using graph structures
    Patent number: 11429876
    Abstract: One embodiment of the invention provides a method for natural language processing (NLP). The method comprises extracting knowledge outside of text content of a NLP instance by extracting a set of subgraphs from a knowledge graph associated with the text content. The set of subgraphs comprises the knowledge. The method further comprises encoding the knowledge with the text content into a fixed size graph representation by filtering and encoding the set of subgraphs. The method further comprises applying a text embedding algorithm to the text content to generate a fixed size text representation, and classifying the text content based on the fixed size graph representation and the fixed size text representation.
    Type: Grant
    Filed: March 10, 2020
    Date of Patent: August 30, 2022
    Assignee: International Business Machines Corporation
    Inventors: Pavan Kapanipathi Bangalore, Kartik Talamadupula, Veronika Thost, Siva Sankalp Patel, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Achille Belly Fokoue-Nkoutche
  • INFUSING KNOWLEDGE INTO NATURAL LANGUAGE PROCESSING TASKS USING GRAPH STRUCTURES
    Publication number: 20210287103
    Abstract: One embodiment of the invention provides a method for natural language processing (NLP). The method comprises extracting knowledge outside of text content of a NLP instance by extracting a set of subgraphs from a knowledge graph associated with the text content. The set of subgraphs comprises the knowledge. The method further comprises encoding the knowledge with the text content into a fixed size graph representation by filtering and encoding the set of subgraphs. The method further comprises applying a text embedding algorithm to the text content to generate a fixed size text representation, and classifying the text content based on the fixed size graph representation and the fixed size text representation.
    Type: Application
    Filed: March 10, 2020
    Publication date: September 16, 2021
    Inventors: Pavan Kapanipathi Bangalore, Kartik Talamadupula, Veronika Thost, Siva Sankalp Patel, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Achille Belly Fokoue-Nkoutche
  • MODEL AGNOSTIC CONTRASTIVE EXPLANATIONS FOR STRUCTURED DATA
    Publication number: 20200193243
    Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.
    Type: Application
    Filed: December 12, 2018
    Publication date: June 18, 2020
    Inventors: Amit Dhurandhar, Pin-Yu Chen, Karthikeyan Shanmugam, Tejaswini Pedapati, Avinash Balakrishnan, Ruchir Puri
  • CONSTRAINED DECISION-MAKING AND EXPLANATION OF A RECOMMENDATION
    Publication number: 20200019871
    Abstract: Systems, computer-implemented methods, and computer program products to facilitate constrained decision-making and explanation of a recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a recommendation component that can recommend a decision based on one or more decision policies. The decision can comply with one or more constraints of a constrained decision policy. The computer executable components can further comprise an explanation component that can generate an explanation of the decision. The explanation can comprise one or more factors contributing to the decision.
    Type: Application
    Filed: July 31, 2018
    Publication date: January 16, 2020
    Inventors: Avinash Balakrishnan, Djallel Bouneffouf, Nicholas Mattei, Francesca Rossi