Patents by Inventor William G. Visotski

William G. Visotski 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: 10083398
    Abstract: An approach is provided in which a knowledge manager generates term tokens from terms included in an original text stream, and generates annotation tokens with corresponding term location information. In turn, the knowledge manager generates a knowledge structure that indexes the term tokens into original text fields and indexes the annotation tokens into parallel fields that align to the original text fields based upon the term location information.
    Type: Grant
    Filed: December 13, 2014
    Date of Patent: September 25, 2018
    Assignee: International Business Machines Corporation
    Inventors: Kay Mueller, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Patent number: 9904674
    Abstract: An approach is provided in which a knowledge manager generates syntactic annotation tokens that correspond to syntactic relationships between terms included in a source document. The knowledge manager creates a knowledge structure that stores the syntactic annotation tokens in parallel fields and stores the source document terms in original text fields, which align to the parallel fields. In turn, the knowledge manager utilizes the knowledge structure to generate answers to questions based upon the syntactic annotation tokens.
    Type: Grant
    Filed: September 21, 2015
    Date of Patent: February 27, 2018
    Assignee: International Business Machines Corporation
    Inventors: Stephen A. Boxwell, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Patent number: 9792280
    Abstract: Mechanisms are provided for performing context based synonym filtering for natural language processing. Content is parsed into one or more conceptual units, wherein each conceptual unit comprises a portion of text of the content that is associated with a single concept. For each conceptual unit, a term in the conceptual unit is identified that has a synonym to be utilized during natural language processing of the content. A first measure of relatedness of the term to at least one other term in the conceptual unit is determined. A second measure of relatedness of the synonym of the term to the at least one other term in the conceptual unit is determined. A determination whether or not to utilize the synonym when performing natural language processing on the conceptual unit is made based on the first and second measures of relatedness and natural language processing on the content is performed accordingly.
    Type: Grant
    Filed: June 3, 2016
    Date of Patent: October 17, 2017
    Assignee: International Business Machines Corporation
    Inventors: Kay Mueller, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Patent number: 9734238
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Grant
    Filed: November 11, 2016
    Date of Patent: August 15, 2017
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Patent number: 9727637
    Abstract: A mechanism is provided for retrieving candidate answers from a corpus of documents. The mechanism receives an input question for which an answer is sought. The mechanism extracts features of the input question based on a natural language processing. The mechanism executes a first search of the corpus of documents based on a first subset of the extracted features of the input question and an initial evaluation of a utility of the first subset of extracted features to generate a subset of documents. The mechanism executes a second search of a set of passages extracted from the subset of documents based on a second subset of the extracted features of the input question and a reevaluation of the utility of the second subset of extracted features thereby forming a subset of passages. The mechanism generates query results from the subset of passages matching from which candidate answers are identified.
    Type: Grant
    Filed: August 19, 2014
    Date of Patent: August 8, 2017
    Assignee: International Business Machines Corporation
    Inventors: William G. Visotski, David E. Wilson
  • Patent number: 9720905
    Abstract: An approach is provided in which a knowledge manager generates syntactic annotation tokens that correspond to syntactic relationships between terms included in a source document. The knowledge manager creates a knowledge structure that stores the syntactic annotation tokens in parallel fields and stores the source document terms in original text fields, which align to the parallel fields. In turn, the knowledge manager utilizes the knowledge structure to generate answers to questions based upon the syntactic annotation tokens.
    Type: Grant
    Filed: June 22, 2015
    Date of Patent: August 1, 2017
    Assignee: International Business Machines Corporation
    Inventors: Stephen A. Boxwell, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Patent number: 9613133
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Grant
    Filed: November 7, 2014
    Date of Patent: April 4, 2017
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Publication number: 20170068726
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Application
    Filed: November 11, 2016
    Publication date: March 9, 2017
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Patent number: 9558263
    Abstract: Mechanisms are provided for identifying commonalities between candidate answers generated by a Question and Answer (QA) system in response to an input question. The mechanisms receive a plurality of candidate answers for an input question from the QA system and identify terms present in the candidate answers. The mechanisms determine relationships between terms in each of the candidate answers and determine a common relationship between a first term and a second term, the common relationship being common amongst at least a subset of the plurality of candidate answers, based on the determined relationships between terms in each of the candidate answers. The mechanisms present the plurality of candidate answers and the common relationship to a user.
    Type: Grant
    Filed: December 5, 2013
    Date of Patent: January 31, 2017
    Assignee: International Business Machines Corporation
    Inventors: William G. Visotski, David E. Wilson, Robert L. Yates
  • Patent number: 9558264
    Abstract: Mechanisms are provided for identifying commonalities between candidate answers generated by a Question and Answer (QA) system in response to an input question. The mechanisms receive a plurality of candidate answers for an input question from the QA system and identify terms present in the candidate answers. The mechanisms determine relationships between terms in each of the candidate answers and determine a common relationship between a first term and a second term, the common relationship being common amongst at least a subset of the plurality of candidate answers, based on the determined relationships between terms in each of the candidate answers. The mechanisms present the plurality of candidate answers and the common relationship to a user.
    Type: Grant
    Filed: February 15, 2016
    Date of Patent: January 31, 2017
    Assignee: International Business Machines Corporation
    Inventors: William G. Visotski, David E. Wilson, Robert L. Yates
  • Patent number: 9529894
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Grant
    Filed: February 16, 2016
    Date of Patent: December 27, 2016
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Publication number: 20160371247
    Abstract: An approach is provided in which a knowledge manager generates syntactic annotation tokens that correspond to syntactic relationships between terms included in a source document. The knowledge manager creates a knowledge structure that stores the syntactic annotation tokens in parallel fields and stores the source document terms in original text fields, which align to the parallel fields. In turn, the knowledge manager utilizes the knowledge structure to generate answers to questions based upon the syntactic annotation tokens.
    Type: Application
    Filed: June 22, 2015
    Publication date: December 22, 2016
    Inventors: Stephen A. Boxwell, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Publication number: 20160371253
    Abstract: An approach is provided in which a knowledge manager generates syntactic annotation tokens that correspond to syntactic relationships between terms included in a source document. The knowledge manager creates a knowledge structure that stores the syntactic annotation tokens in parallel fields and stores the source document terms in original text fields, which align to the parallel fields. In turn, the knowledge manager utilizes the knowledge structure to generate answers to questions based upon the syntactic annotation tokens.
    Type: Application
    Filed: September 21, 2015
    Publication date: December 22, 2016
    Inventors: Stephen A. Boxwell, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Publication number: 20160283468
    Abstract: Mechanisms are provided for performing context based synonym filtering for natural language processing. Content is parsed into one or more conceptual units, wherein each conceptual unit comprises a portion of text of the content that is associated with a single concept. For each conceptual unit, a term in the conceptual unit is identified that has a synonym to be utilized during natural language processing of the content. A first measure of relatedness of the term to at least one other term in the conceptual unit is determined. A second measure of relatedness of the synonym of the term to the at least one other term in the conceptual unit is determined. A determination whether or not to utilize the synonym when performing natural language processing on the conceptual unit is made based on the first and second measures of relatedness and natural language processing on the content is performed accordingly.
    Type: Application
    Filed: June 3, 2016
    Publication date: September 29, 2016
    Inventors: KAY MUELLER, CHRISTOPHER M. NOLAN, WILLIAM G. VISOTSKI, DAVID E. WILSON
  • Publication number: 20160224663
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Application
    Filed: February 16, 2016
    Publication date: August 4, 2016
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Patent number: 9378204
    Abstract: Mechanisms are provided for performing context based synonym filtering for natural language processing. Content is parsed into one or more conceptual units, wherein each conceptual unit comprises a portion of text of the content that is associated with a single concept. For each conceptual unit, a term in the conceptual unit is identified that has a synonym to be utilized during natural language processing of the content. A first measure of relatedness of the term to at least one other term in the conceptual unit is determined. A second measure of relatedness of the synonym of the term to the at least one other term in the conceptual unit is determined. A determination whether or not to utilize the synonym when performing natural language processing on the conceptual unit is made based on the first and second measures of relatedness and natural language processing on the content is performed accordingly.
    Type: Grant
    Filed: May 22, 2014
    Date of Patent: June 28, 2016
    Assignee: International Business Machines Corporation
    Inventors: Kay Mueller, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Publication number: 20160171095
    Abstract: Mechanisms are provided for identifying commonalities between candidate answers generated by a Question and Answer (QA) system in response to an input question. The mechanisms receive a plurality of candidate answers for an input question from the QA system and identify terms present in the candidate answers. The mechanisms determine relationships between terms in each of the candidate answers and determine a common relationship between a first term and a second term, the common relationship being common amongst at least a subset of the plurality of candidate answers, based on the determined relationships between terms in each of the candidate answers. The mechanisms present the plurality of candidate answers and the common relationship to a user.
    Type: Application
    Filed: February 15, 2016
    Publication date: June 16, 2016
    Inventors: William G. Visotski, David E. Wilson, Robert L. Yates
  • Publication number: 20160171092
    Abstract: An approach is provided in which a knowledge manager generates term tokens from terms included in an original text stream, and generates annotation tokens with corresponding term location information. In turn, the knowledge manager generates a knowledge structure that indexes the term tokens into original text fields and indexes the annotation tokens into parallel fields that align to the original text fields based upon the term location information.
    Type: Application
    Filed: December 13, 2014
    Publication date: June 16, 2016
    Inventors: Kay Mueller, Christopher M. Nolan, William G. Visotski, David E. Wilson
  • Publication number: 20160132589
    Abstract: According to an aspect, a question answering computer system determines a set of search terms for a given question. A plurality of passages that each includes at least one search term in the set of search terms is identified in response to a search of a document for search terms in the set of search terms. A passage from the plurality of passages is selected. A context based score of the selected passage that indicates the likelihood that the selected passage contains an answer to the question is generated based on criteria that specify a relationship among the set of search terms, content of the passage, and content of at least one other passage in the plurality of passages.
    Type: Application
    Filed: November 7, 2014
    Publication date: May 12, 2016
    Inventors: Christopher M. Nolan, William G. Visotski, David E. Wilson, Robert L. Yates
  • Publication number: 20160055234
    Abstract: A mechanism is provided for retrieving candidate answers from a corpus of documents. The mechanism receives an input question for which an answer is sought. The mechanism extracts features of the input question based on a natural language processing. The mechanism executes a first search of the corpus of documents based on a first subset of the extracted features of the input question and an initial evaluation of a utility of the first subset of extracted features to generate a subset of documents. The mechanism executes a second search of a set of passages extracted from the subset of documents based on a second subset of the extracted features of the input question and a reevaluation of the utility of the second subset of extracted features thereby forming a subset of passages. The mechanism generates query results from the subset of passages matching from which candidate answers are identified.
    Type: Application
    Filed: August 19, 2014
    Publication date: February 25, 2016
    Inventors: William G. Visotski, David E. Wilson