Patents by Inventor John F. Pitrelli

John F. Pitrelli 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: 11100140
    Abstract: Embodiments provide a computer implemented method in a data processing system including a processor and a memory, the memory including instructions that are executed by the processor to cause the processor to implement a system for generating a type system. The method includes: receiving a document corpus; identifying frequently occurring words from the document corpus, disregarding stop words; extracting a conceptual text for each frequently occurring word from a structured information database; performing a cluster analysis on each conceptual text to identify possible entity types; performing a frequency analysis on possible entity types to select at least one entity type; identifying a relation type between entities in the document corpus; and generating the type system including entity types and relation types.
    Type: Grant
    Filed: June 4, 2018
    Date of Patent: August 24, 2021
    Assignee: International Business Machines Corporation
    Inventors: Avinash Asthana, John F. Pitrelli, Edward J. Biddle, Vijai Gandikota
  • Publication number: 20200311343
    Abstract: Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.
    Type: Application
    Filed: November 1, 2019
    Publication date: October 1, 2020
    Applicant: Nuance Communications, Inc.
    Inventors: Neal E. Snider, Brian William Delaney, Girija Yegnanarayanan, Radu Florian, Martin Franz, Scott McCarley, John F. Pitrelli, Imed Zitouni, Salim E. Roukos
  • Publication number: 20200160231
    Abstract: A method, system, apparatus, and a computer program product are provided for identifying ground truth annotators by applying statistical analyses to a document corpus and to a plurality of annotator profiles to identify, respectively, corpus complexity attributes for the document corpus and annotator qualification attributes for each candidate annotator which are compared with a matching analysis to identify one or more recommended annotators from the plurality of candidate annotators based on the matching analysis.
    Type: Application
    Filed: November 19, 2018
    Publication date: May 21, 2020
    Inventors: Avinash Asthana, John F. Pitrelli, Swami Chandrasekaran, Edward J. Biddle
  • Publication number: 20190370385
    Abstract: Embodiments provide a computer implemented method in a data processing system including a processor and a memory, the memory including instructions that are executed by the processor to cause the processor to implement a system for generating a type system. The method includes: receiving a document corpus; identifying frequently occurring words from the document corpus, disregarding stop words; extracting a conceptual text for each frequently occurring word from a structured information database; performing a cluster analysis on each conceptual text to identify possible entity types; performing a frequency analysis on possible entity types to select at least one entity type; identifying a relation type between entities in the document corpus; and generating the type system including entity types and relation types.
    Type: Application
    Filed: June 4, 2018
    Publication date: December 5, 2019
    Inventors: Avinash Asthana, John F. Pitrelli, Edward J. Biddle, Vijai Gandikota
  • Patent number: 10496743
    Abstract: Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.
    Type: Grant
    Filed: June 26, 2013
    Date of Patent: December 3, 2019
    Assignee: Nuance Communications, Inc.
    Inventors: Neal E. Snider, Brian William Delaney, Girija Yegnanarayanan, Radu Florian, Martin Franz, Scott McCarley, John F. Pitrelli, Imed Zitouni, Salim E. Roukos
  • Publication number: 20150006199
    Abstract: Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.
    Type: Application
    Filed: June 26, 2013
    Publication date: January 1, 2015
    Inventors: Neal E. Snider, Brian William Delaney, Girija Yegnanarayanan, Radu Florian, Martin Franz, Scott McCarley, John F. Pitrelli, Imed Zitouni, Salim E. Roukos
  • Patent number: 6567548
    Abstract: A handwriting recognition system and method whereby various character sequences (which are typically “slurred” together when handwritten) are each modelled as a single character (“compound character model”) so as to provide increased decoding accuracy for slurred handwritten character sequences. In one aspect of the present invention, a method for generating a handwriting recognition system having compound character models comprises the steps of: providing an initial handwriting recognition system having individual character models; collecting and labelling a set of handwriting data; aligning the labelled set of handwriting data; generating compound character data using the aligned handwriting data; and retraining the initial recognition system with the compound character data to generate a new recognition system having compound character models.
    Type: Grant
    Filed: January 29, 1999
    Date of Patent: May 20, 2003
    Assignee: International Business Machines Corporation
    Inventors: Krishna S. Nathan, Michael P. Perrone, John F. Pitrelli
  • Publication number: 20020143654
    Abstract: A telecommunication system includes a communication network having a plurality of switches that are coupled between at least one transaction server, a plurality of receiver premises and a plurality of marketer premises. The transaction server includes memory for storing receiver data corresponding to a receiver identifier and a processor unit. The transaction server further includes a control mechanism to operate the switches to establish communication pathways between any marketer premises and any receiver premises. In the operation of the invention, the transaction server receives a receiver identifier and offer terms from a marketer premises, establishes a communication pathway with a receiver premises corresponding to the receiver identifier and asks if the receiver premises wishes to receive information from the marketer premises. Upon an acceptance, the transaction server enables provision of the information.
    Type: Application
    Filed: February 15, 2002
    Publication date: October 3, 2002
    Applicant: NYNEX SCIENCE AND TECHNOLOGY, INC.
    Inventors: Kuansan Wang, John F. Pitrelli
  • Publication number: 20020067852
    Abstract: A handwriting recognition system and method whereby various character sequences (which are typically “slurred” together when handwritten) are each modelled as a single character (“compound character model” ) so as to provide increased decoding accuracy for slurred handwritten character sequences. In one aspect of the present invention, a method for generating a handwriting recognition system having compound character models comprises the steps of: providing an initial handwriting recognition system having individual character models; collecting and labelling a set of handwriting data; aligning the labelled set of handwriting data; generating compound character data using the aligned handwriting data; and retraining the initial recognition system with the compound character data to generate a new recognition system having compound character models.
    Type: Application
    Filed: January 29, 1999
    Publication date: June 6, 2002
    Inventors: KRISHNA S. NATHAN, MICHAEL P. PERRONE, JOHN F. PITRELLI
  • Patent number: 6401067
    Abstract: A data recognition system and method which allows a user to select between a “default recognition” mode and a “constrained recognition” mode via a user interface. In the default recognition mode, a recognition engine utilizes predetermined default recognition parameters to decode data (e.g., handwriting and speech). In the constrained recognition mode, the user can select one or more of a plurality of recognition constraints which temporarily modify the default recognition parameters to decode uncharacteristic and/or special data. The recognition parameters associated with the selected constraint enable the recognition engine to utilize specific information to decode the special data, thereby providing increased recognition accuracy.
    Type: Grant
    Filed: January 28, 1999
    Date of Patent: June 4, 2002
    Assignee: International Business Machines Corporation
    Inventors: James R. Lewis, Michael P. Perrone, John F. Pitrelli, Eugene H. Ratzlaff, Jayashree Subrahmonia
  • Publication number: 20010053978
    Abstract: A data recognition system and method which allows a user to select between a “default recognition” mode and a “constrained recognition” mode via a user interface. In the default recognition mode, a recognition engine utilizes predetermined default recognition parameters to decode data (e.g., handwriting and speech). In the constrained recognition mode, the user can select one or more of a plurality of recognition constraints which temporarily modify the default recognition parameters to decode uncharacteristic and/or special data. The recognition parameters associated with the selected constraint enable the recognition engine to utilize specific information to decode the special data, thereby providing increased recognition accuracy.
    Type: Application
    Filed: January 28, 1999
    Publication date: December 20, 2001
    Inventors: JAMES R. LEWIS, MICHAEL P. PERRONE, JOHN F. PITRELLI, EUGENE H. RATZLAFF, JAYASHREE SUBRAHMONIA
  • Patent number: 6326957
    Abstract: System and methods for visually displaying page information in a handwriting recording device such as a personal digital notepad (PDN) device, in which constraints exist which limit the size of a user interface display (e.g. LCD). Various methods allow a user to view detailed page information by selecting one or more available display modes which display the selected information using one or more dynamic icons. In addition, the user can view (via the display) selected portions of handwriting content of a given electronic page, thereby affording the user the opportunity to synchronize the stored handwriting data with the handwritten text.
    Type: Grant
    Filed: January 29, 1999
    Date of Patent: December 4, 2001
    Assignee: International Business Machines Corporation
    Inventors: Krishna S. Nathan, Michael P. Perrone, John F. Pitrelli, Eugene H. Ratzlaff, Jayashree Subrahmonia