Patents by Inventor Anthony T. Levas
Anthony T. Levas 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).
-
Publication number: 20160005324Abstract: The present disclosure relates generally to question answering systems and methods and, particularly, to systems and methods for domain adaptation in question answering.Type: ApplicationFiled: September 15, 2015Publication date: January 7, 2016Inventors: Sugato Bagchi, David A. Ferrucci, David C. Gondek, Anthony T. Levas, Wlodek W. Zadrozny
-
Publication number: 20160005325Abstract: The present disclosure relates generally to question answering systems and methods and, particularly, to systems and methods for domain adaptation in question answering.Type: ApplicationFiled: September 15, 2015Publication date: January 7, 2016Inventors: Sugato Bagchi, David A. Ferrucci, David C. Gondek, Anthony T. Levas, Wlodek W. Zadrozny
-
Patent number: 9189541Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: GrantFiled: September 23, 2011Date of Patent: November 17, 2015Assignee: International Business Machines CorporationInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Patent number: 9189542Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: GrantFiled: September 14, 2012Date of Patent: November 17, 2015Assignee: International Business Machines CorporationInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Patent number: 9153142Abstract: Systems and methods display at least one subject, and display a location for at least one user to enter at least one problem related to the subject. The problem comprises unknown items to which the user would like more information. In response to the problem, such systems and methods automatically generate evidence topics related to the problem, and automatically generate questions related to the problem and the evidence topics. Further, such systems and methods can receive additional questions from the user. In response to the questions, such systems and methods automatically generate answers to the questions by referring to sources, automatically calculate confidence measures of each of the answers, and then display the questions, the answers, and the confidence measures. When the user identifies one of the answers as a selected answer, such systems and methods display details of the sources and the factors used to generate the selected answer.Type: GrantFiled: April 17, 2012Date of Patent: October 6, 2015Assignee: International Business Machines CorporationInventors: Sugato Bagchi, Michael A. Barborak, Steven D. Daniels, David A. Ferrucci, Anthony T. Levas
-
Patent number: 9031832Abstract: Context-based disambiguation of acronyms and/or abbreviations may determine a target abbreviation and one or more keywords appearing in context with the target abbreviation in a received passage, the target abbreviation representing a shortened form of one or more word. A contextual search query including the target abbreviation and said one or more keywords may be generated. A pseudo document index may be searched for one or more expansions of the target abbreviation by invoking the contextual search query, the pseudo document index containing index of one or more pseudo documents, associated one or more abbreviations and associated context keywords. One or more pseudo documents associated with the target abbreviation may be returned based on the searching of the pseudo document index.Type: GrantFiled: September 6, 2012Date of Patent: May 12, 2015Assignee: International Business Machines CorporationInventors: Branimir K. Boguraev, Jennifer Chu-Carroll, David A. Ferrucci, Anthony T. Levas, John M. Prager
-
Patent number: 9020805Abstract: Context-based disambiguation of acronyms and/or abbreviations may determine a target abbreviation and one or more keywords appearing in context with the target abbreviation in a received passage, the target abbreviation representing a shortened form of one or more word. A contextual search query including the target abbreviation and said one or more keywords may be generated. A pseudo document index may be searched for one or more expansions of the target abbreviation by invoking the contextual search query, the pseudo document index containing index of one or more pseudo documents, associated one or more abbreviations and associated context keywords. One or more pseudo documents associated with the target abbreviation may be returned based on the searching of the pseudo document index.Type: GrantFiled: September 23, 2011Date of Patent: April 28, 2015Assignee: International Business Machines CorporationInventors: Branimir K. Boguraev, Jennifer Chu-Carroll, David A. Ferrucci, Anthony T. Levas, John M. Prager
-
Patent number: 9002773Abstract: A decision-support system for problem solving comprises software modules embodied on a computer readable medium, and the software modules comprise an input/output module and a question-answering module. The method receives problem case information using the input/output module, generates a query based on the problem case information, and generates a plurality of answers for the query using the question-answering module. The method also calculates numerical values for multiple evidence dimensions from evidence sources for each of the answers using the question-answering module and calculates a corresponding confidence value for each of the answers based on the numerical value of each evidence dimension using the question-answering module. Further, the method outputs the answers, the corresponding confidence values, and the numerical values of each evidence dimension for one or more selected answers using the input/output module.Type: GrantFiled: March 31, 2011Date of Patent: April 7, 2015Assignee: International Business Machines CorporationInventors: Sugato Bagchi, David A. Ferrucci, Anthony T. Levas, Erik T Mueller
-
Publication number: 20140164304Abstract: In a method of answering questions and scoring answers, a title and at least one topical field are identified for a document. A field name and field content associated with the topical field is identified, and a title-oriented document is created by combining the title, the field name, and the field content associated with the topical field. For each title-oriented document, a term in the title is matched to previously established categories to produce a title concept identifier. The topical field is synthesized to produce a field concept identifier and a field content concept identifier. A question is received. The question topic term and the question content identifier are used to identify at least one question-matching relation instance. The title concept identifier of each question-matching relation instance is identified as a candidate answer to the question. Each candidate answer and a corresponding answer score is output.Type: ApplicationFiled: December 11, 2012Publication date: June 12, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, David A. Ferrucci, Anthony T. Levas, Erik T. Mueller
-
Publication number: 20140164303Abstract: In a method of answering questions and scoring answers, a title and at least one topical field are identified for a document. A field name and field content associated with the topical field is identified, and a title-oriented document is created by combining the title, the field name, and the field content associated with the topical field. For each title-oriented document, a term in the title is matched to previously established categories to produce a title concept identifier. The topical field is synthesized to produce a field concept identifier and a field content concept identifier. A question is received. The question topic term and the question content identifier are used to identify at least one question-matching relation instance. The title concept identifier of each question-matching relation instance is identified as a candidate answer to the question. Each candidate answer and a corresponding answer score is output.Type: ApplicationFiled: December 11, 2012Publication date: June 12, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, David A. Ferrucci, Anthony T. Levas, Erik T. Mueller
-
Publication number: 20130013547Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: ApplicationFiled: September 14, 2012Publication date: January 10, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Publication number: 20130013546Abstract: A system for providing community for customer questions receives a customer question. The customer question may be classified into a classification from a plurality of classifications categorizing whether a question is answerable, needs expert assistance, needs more information, or is not answerable. Based on the classification and one or more incentives, the question may be further routed to an appropriate community. The interactions with a customer in receiving and answering the customer question may be recorded.Type: ApplicationFiled: September 14, 2012Publication date: January 10, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, Branimir K. Boguraev, Anthony T. Levas, Roberto Sicconi, Wlodek W. Zadrozny
-
Publication number: 20120330648Abstract: Context-based disambiguation of acronyms and/or abbreviations may determine a target abbreviation and one or more keywords appearing in context with the target abbreviation in a received passage, the target abbreviation representing a shortened form of one or more word. A contextual search query including the target abbreviation and said one or more keywords may be generated. A pseudo document index may be searched for one or more expansions of the target abbreviation by invoking the contextual search query, the pseudo document index containing index of one or more pseudo documents, associated one or more abbreviations and associated context keywords. One or more pseudo documents associated with the target abbreviation may be returned based on the searching of the pseudo document index.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Branimir K. Boguraev, Jennifer Chu-Carroll, David A. Ferrucci, Anthony T. Levas, John M. Prager
-
Publication number: 20120301864Abstract: Systems and methods display at least one subject, and display a location for at least one user to enter at least one problem related to the subject. The problem comprises unknown items to which the user would like more information. In response to the problem, such systems and methods automatically generate evidence topics related to the problem, and automatically generate questions related to the problem and the evidence topics. Further, such systems and methods can receive additional questions from the user. In response to the questions, such systems and methods automatically generate answers to the questions by referring to sources, automatically calculate confidence measures of each of the answers, and then display the questions, the answers, and the confidence measures. When the user identifies one of the answers as a selected answer, such systems and methods display details of the sources and the factors used to generate the selected answer.Type: ApplicationFiled: April 17, 2012Publication date: November 29, 2012Applicant: International Business Machines CorporationInventors: Sugato Bagchi, Michael A. Barborak, Steven D. Daniels, David A. Ferrucci, Anthony T. Levas
-
Patent number: 8200656Abstract: A method, system and computer program product are disclosed for searching for information using a knowledge base. In one embodiment, the method comprises receiving a query; formulizing the query, including dividing the query into a plurality of parts; for each of the parts, identifying a source, using the knowledge, that addresses that part; and combining the sources to answer the query. In one embodiment, the query includes text; the text is separated into a plurality of segments; and, for each of the segments, at least one source is identified addressing the segment. In an embodiment, a logical proof is formulated having a conclusion that is an answer to the query, and a sequence of statements that establish said conclusion; and a proof of this conclusion is generated by identifying two or more documents that assert the sequence of statements.Type: GrantFiled: November 17, 2009Date of Patent: June 12, 2012Assignee: International Business Machines CorporationInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James William Murdock, IV
-
Publication number: 20120131016Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: ApplicationFiled: September 23, 2011Publication date: May 24, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Publication number: 20120084112Abstract: A system for providing community for customer questions receives a customer question. The customer question may be classified into a classification from a plurality of classifications categorizing whether a question is answerable, needs expert assistance, needs more information, or is not answerable. Based on the classification and one or more incentives, the question may be further routed to an appropriate community. The interactions with a customer in receiving and answering the customer question may be recorded.Type: ApplicationFiled: September 24, 2011Publication date: April 5, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, Branimir K. Boguraev, Anthony T. Levas, Roberto Sicconi, Wlodek W. Zadrozny
-
Publication number: 20120084076Abstract: Context-based disambiguation of acronyms and/or abbreviations may determine a target abbreviation and one or more keywords appearing in context with the target abbreviation in a received passage, the target abbreviation representing a shortened form of one or more word. A contextual search query including the target abbreviation and said one or more keywords may be generated. A pseudo document index may be searched for one or more expansions of the target abbreviation by invoking the contextual search query, the pseudo document index containing index of one or more pseudo documents, associated one or more abbreviations and associated context keywords. One or more pseudo documents associated with the target abbreviation may be returned based on the searching of the pseudo document index.Type: ApplicationFiled: September 23, 2011Publication date: April 5, 2012Applicant: International Business Machines CorporationInventors: Branimir K. Boguraev, Jennifer Chu-Carroll, David A. Ferrucci, Anthony T. Levas, John M. Prager
-
Publication number: 20120077178Abstract: The present disclosure relates generally to question answering systems and methods and, particularly, to systems and methods for domain adaptation in question answering.Type: ApplicationFiled: September 24, 2011Publication date: March 29, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, David A. Ferrucci, David C. Gondek, Anthony T. Levas, Wlodek W. Zadrozny
-
Publication number: 20120078062Abstract: A decision-support system for medical diagnosis and treatment comprises software modules embodied on a computer readable medium, and the software modules comprise an input/output module and a question-answering module. The method receives patient case information using the input/output module, and generates a medical diagnosis or treatment query based on the patient case information and also generates a plurality of medical diagnosis or treatment answers for the query using the question-answering module. The method also calculates numerical values for multiple medical evidence dimensions from medical evidence sources for each of the answers using the question-answering module and also calculates a corresponding confidence value for each of the answers based on the numerical value of each evidence dimension using the question-answering module.Type: ApplicationFiled: March 31, 2011Publication date: March 29, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sugato Bagchi, David A. Ferrucci, Anthony T. Levas, Erik T. Mueller