Patents by Inventor Ravi S. Sinha
Ravi S. Sinha 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: 11132370Abstract: Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.Type: GrantFiled: May 20, 2019Date of Patent: September 28, 2021Assignee: International Business Machines CorporationInventors: Amrish V. Chaubal, Kadriye E. Eyigoz, Priscilla Santos Moraes, Ravi S. Sinha
-
Patent number: 10586161Abstract: A mechanism is provided in a data processing system for conducting error analysis for a question answering system. Responsive to the question answering system generating one or more candidate answers for an input question, wherein the one or more candidate answers are determined to be incorrect, the mechanism instantiates a plurality of instances of the question answering system with a modification to each instance. The mechanism provides the input question to each of the plurality of instances of the question answering system. The mechanism analyzes results from the plurality of instances of the question answering system to identify at least one modification that led to improved results. The mechanism presents a graphical output based on the analysis.Type: GrantFiled: November 3, 2015Date of Patent: March 10, 2020Assignee: International Business Machines CorporationInventors: John J. Anderson, Kathryn V. Banks, Blake J. Fox, Ravi S. Sinha
-
Publication number: 20190272277Abstract: Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.Type: ApplicationFiled: May 20, 2019Publication date: September 5, 2019Inventors: Amrish V. Chaubal, Kadriye E. Eyigoz, Priscilla Santos Moraes, Ravi S. Sinha
-
Patent number: 10331684Abstract: Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.Type: GrantFiled: June 3, 2016Date of Patent: June 25, 2019Assignee: International Business Machines CorporationInventors: Amrish V. Chaubal, Kadriye E. Eyigoz, Priscilla Santos Moraes, Ravi S. Sinha
-
Patent number: 10318633Abstract: An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: GrantFiled: January 2, 2017Date of Patent: June 11, 2019Assignee: International Business Machines CorporationInventors: Bharath Dandala, Ravi S. Sinha
-
Patent number: 10318634Abstract: An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: GrantFiled: January 2, 2017Date of Patent: June 11, 2019Assignee: International Business Machines CorporationInventors: Bharath Dandala, Ravi S. Sinha
-
Patent number: 10303764Abstract: An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: GrantFiled: June 8, 2017Date of Patent: May 28, 2019Assignee: International Business Machines CorporationInventors: Bharath Dandala, Ravi S. Sinha
-
Patent number: 10303765Abstract: An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: GrantFiled: June 8, 2017Date of Patent: May 28, 2019Assignee: International Business Machines CorporationInventors: Bharath Dandala, Ravi S. Sinha
-
Publication number: 20180189263Abstract: An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: ApplicationFiled: June 8, 2017Publication date: July 5, 2018Inventors: Bharath Dandala, Ravi S. Sinha
-
Publication number: 20180189261Abstract: An approach is provided that receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: ApplicationFiled: January 2, 2017Publication date: July 5, 2018Inventors: Bharath Dandala, Ravi S. Sinha
-
Publication number: 20180189264Abstract: An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: ApplicationFiled: June 8, 2017Publication date: July 5, 2018Inventors: Bharath Dandala, Ravi S. Sinha
-
Publication number: 20180189262Abstract: An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.Type: ApplicationFiled: January 2, 2017Publication date: July 5, 2018Inventors: Bharath Dandala, Ravi S. Sinha
-
Publication number: 20170351677Abstract: Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.Type: ApplicationFiled: June 3, 2016Publication date: December 7, 2017Inventors: Amrish V. Chaubal, Kadriye E. Eyigoz, Priscilla Santos Moraes, Ravi S. Sinha
-
Patent number: 9720910Abstract: An approach is provided to receive a term that is included in a Business Process Model (BPM) data store with the term being from one natural language. The approach identifies that first descriptive text of the term is not available in the same natural language. A translated version of the term is retrieved from a different natural language stored in the BPM data store with descriptive text of the term being present in the different language. The descriptive text is translated to the given natural language, resulting in translated descriptive text that is, in turn, provided as a meaning of the term in the given language.Type: GrantFiled: November 11, 2015Date of Patent: August 1, 2017Assignee: International Business Machines CorporationInventors: Donna K. Byron, Lakshminarayanan Krishnamurthy, Ravi S. Sinha, Craig M. Trim
-
Publication number: 20170132213Abstract: An approach is provided to receive a term that is included in a Business Process Model (BPM) data store with the term being from one natural language. The approach identifies that first descriptive text of the term is not available in the same natural language. A translated version of the term is retrieved from a different natural language stored in the BPM data store with descriptive text of the term being present in the different language. The descriptive text is translated to the given natural language, resulting in translated descriptive text that is, in turn, provided as a meaning of the term in the given language.Type: ApplicationFiled: November 11, 2015Publication date: May 11, 2017Inventors: Donna K. Byron, Lakshminarayanan Krishnamurthy, Ravi S. Sinha, Craig M. Trim
-
Publication number: 20170124475Abstract: A mechanism is provided in a data processing system for conducting error analysis for a question answering system. Responsive to the question answering system generating one or more candidate answers for an input question, wherein the one or more candidate answers are determined to be incorrect, the mechanism instantiates a plurality of instances of the question answering system with a modification to each instance. The mechanism provides the input question to each of the plurality of instances of the question answering system. The mechanism analyzes results from the plurality of instances of the question answering system to identify at least one modification that led to improved results. The mechanism presents a graphical output based on the analysis.Type: ApplicationFiled: November 3, 2015Publication date: May 4, 2017Inventors: John J. Anderson, Kathryn V. Banks, Blake J. Fox, Ravi S. Sinha