Patents by Inventor Kandhan Sekar
Kandhan Sekar 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: 11593561Abstract: A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.Type: GrantFiled: September 11, 2019Date of Patent: February 28, 2023Assignee: International Business Machines CorporationInventors: David Contreras, Krishna Mahajan, Roberto Delima, Kandhan Sekar, Corville O. Allen, Chris Mwarabu
-
Patent number: 11334720Abstract: A method, system, and computer program product for using a natural language processor includes importing a training text including a plurality of training nodes and having a first marked span that includes some of the plurality of training nodes and a first training trigger, wherein each training node includes a first attribute and a second attribute. Also included are generating a first plurality of training tree tables for each training node with respect to a first training traversal from the first training trigger, each training tree table including the first and second attributes of each training node in the first training traversal, and generating a first plurality of training comparison tables from the first plurality of training tree tables. Each training comparison table is also analyzed to determine if a target node belongs in the first marked span, and labeling each training comparison table accordingly.Type: GrantFiled: April 17, 2019Date of Patent: May 17, 2022Assignee: International Business Machines CorporationInventors: Joshua Cason, Kandhan Sekar, Thomas Hay Rogers
-
Patent number: 11275892Abstract: A method, system, and computer program product for using a natural language processor to find nodes in a span include providing a parse tree including a trigger node, a first target node connected to the trigger node by a first edge, and a second target node connected to the first target node by a second edge, wherein first trigger node includes a first attribute and a second attribute, and wherein the target node includes a third attribute and a fourth attribute. Further included are recording the first, second, third, and fourth attributes in a first tree table; creating a first consideration table from the first tree table, the first consideration table including the first, second, third, and fourth attributes; and evaluating the first target node to determine whether the first node belongs in a first span that includes the first trigger node.Type: GrantFiled: April 29, 2019Date of Patent: March 15, 2022Assignee: International Business Machines CorporationInventors: Joshua Cason, Kandhan Sekar, Thomas Hay Rogers
-
Patent number: 11205053Abstract: Methods, systems and computer readable media are provided for semantic evaluation of tentative triggers based on contextual triggers. Contextual triggers are identified within text. A parse tree comprising a plurality of nodes is generated corresponding to the text. Tentative triggers are identified within the text. A determination is made as to whether one or more nodes of the parse tree corresponding to the tentative trigger is within a context of one or more nodes of the parse tree corresponding to the contextual triggers. Based on the determination, the tentative trigger type is assigned to a contextual trigger type.Type: GrantFiled: March 26, 2020Date of Patent: December 21, 2021Assignee: International Business Machines CorporationInventors: David Contreras, Kandhan Sekar, Thomas Hay Rogers
-
Publication number: 20210303794Abstract: Methods, systems and computer readable media are provided for semantic evaluation of tentative triggers based on contextual triggers. Contextual triggers are identified within text. A parse tree comprising a plurality of nodes is generated corresponding to the text. Tentative triggers are identified within the text. A determination is made as to whether one or more nodes of the parse tree corresponding to the tentative trigger is within a context of one or more nodes of the parse tree corresponding to the contextual triggers. Based on the determination, the tentative trigger type is assigned to a contextual trigger type.Type: ApplicationFiled: March 26, 2020Publication date: September 30, 2021Inventors: David Contreras, Kandhan Sekar, Thomas Hay Rogers
-
Patent number: 11113469Abstract: A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.Type: GrantFiled: March 27, 2019Date of Patent: September 7, 2021Assignee: International Business Machines CorporationInventors: Corville O. Allen, Roberto Delima, Chris Mwarabu, David Contreras, Kandhan Sekar, Krishna Mahajan
-
Publication number: 20200342054Abstract: A method, system, and computer program product for using a natural language processor to find nodes in a span include providing a parse tree including a trigger node, a first target node connected to the trigger node by a first edge, and a second target node connected to the first target node by a second edge, wherein first trigger node includes a first attribute and a second attribute, and wherein the target node includes a third attribute and a fourth attribute. Further included are recording the first, second, third, and fourth attributes in a first tree table; creating a first consideration table from the first tree table, the first consideration table including the first, second, third, and fourth attributes; and evaluating the first target node to determine whether the first node belongs in a first span that includes the first trigger node.Type: ApplicationFiled: April 29, 2019Publication date: October 29, 2020Inventors: Joshua Cason, Kandhan Sekar, Thomas Hay Rogers
-
Publication number: 20200334331Abstract: A method, system, and computer program product for using a natural language processor includes importing a training text including a plurality of training nodes and having a first marked span that includes some of the plurality of training nodes and a first training trigger, wherein each training node includes a first attribute and a second attribute. Also included are generating a first plurality of training tree tables for each training node with respect to a first training traversal from the first training trigger, each training tree table including the first and second attributes of each training node in the first training traversal, and generating a first plurality of training comparison tables from the first plurality of training tree tables. Each training comparison table is also analyzed to determine if a target node belongs in the first marked span, and labeling each training comparison table accordingly.Type: ApplicationFiled: April 17, 2019Publication date: October 22, 2020Inventors: Joshua Cason, Kandhan Sekar, Thomas Hay Rogers
-
Publication number: 20200311197Abstract: A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.Type: ApplicationFiled: March 27, 2019Publication date: October 1, 2020Inventors: Corville O. Allen, Roberto Delima, Chris Mwarabu, David Contreras, Kandhan Sekar, Krishna Mahajan
-
Publication number: 20200175116Abstract: A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.Type: ApplicationFiled: September 11, 2019Publication date: June 4, 2020Inventors: David Contreras, Krishna Mahajan, Roberto Delima, Kandhan Sekar, Corville O. Allen, Chris Mwarabu