Patents by Inventor Martin Abente Lahaye

Martin Abente Lahaye 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).

  • CROSS-CLASS ONTOLOGY INTEGRATION FOR LANGUAGE MODELING
    Publication number: 20240127797
    Abstract: Provided is a method including obtaining a set of ontologies mapping n-grams onto concepts to which the n-grams refer in different respective domains of knowledge. The method includes receiving an update associating a first n-gram with a first concept and receiving information by which the update is associated with a given domain of knowledge. The method includes selecting a subset of ontologies by determining that the update in the given domain of knowledge is applicable to respective domains of knowledge of the subset of ontologies and that the first concept has a specified type of relationship to a subset of concepts to which other n-grams are mapped in the subset of ontologies. The method also includes storing, in response to the determination, associations between the first n-gram and the subset of concepts in at least some of the subset of ontologies in memory of the computer system.
    Type: Application
    Filed: October 18, 2023
    Publication date: April 18, 2024
    Inventors: Walter Bender, Martin Abente Lahaye, Christopher Liu
  • Cross-class ontology integration for language modeling
    Patent number: 11854531
    Abstract: Provided is a method including obtaining a set of ontologies mapping n-grams onto concepts to which the n-grams refer in different respective domains of knowledge. The method includes receiving an update associating a first n-gram with a first concept and receiving information by which the update is associated with a given domain of knowledge. The method includes selecting a subset of ontologies by determining that the update in the given domain of knowledge is applicable to respective domains of knowledge of the subset of ontologies and that the first concept has a specified type of relationship to a subset of concepts to which other n-grams are mapped in the subset of ontologies. The method also includes storing, in response to the determination, associations between the first n-gram and the subset of concepts in at least some of the subset of ontologies in memory of the computer system.
    Type: Grant
    Filed: March 23, 2021
    Date of Patent: December 26, 2023
    Assignee: Sorcero, Inc.
    Inventors: Walter Bender, Martin Abente Lahaye, Christopher Liu
  • CROSS-CLASS ONTOLOGY INTEGRATION FOR LANGUAGE MODELING
    Publication number: 20210294970
    Abstract: Provided is a method including obtaining a set of ontologies mapping n-grams onto concepts to which the n-grams refer in different respective domains of knowledge. The method includes receiving an update associating a first n-gram with a first concept and receiving information by which the update is associated with a given domain of knowledge. The method includes selecting a subset of ontologies by determining that the update in the given domain of knowledge is applicable to respective domains of knowledge of the subset of ontologies and that the first concept has a specified type of relationship to a subset of concepts to which other n-grams are mapped in the subset of ontologies. The method also includes storing, in response to the determination, associations between the first n-gram and the subset of concepts in at least some of the subset of ontologies in memory of the computer system.
    Type: Application
    Filed: March 23, 2021
    Publication date: September 23, 2021
    Inventors: Walter Bender, Martin Abente Lahaye, Christopher Liu