Patents by Inventor Adam Lally
Adam Lally 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: 10657205Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: May 19, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10650099Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: May 12, 2020Assignee: ELMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10628523Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 21, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10621285Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 14, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10614166Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 7, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10614165Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 7, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10606952Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: June 24, 2016Date of Patent: March 31, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10599778Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: March 24, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034421Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034427Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034422Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034420Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034423Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034424Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034428Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10496754Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: December 3, 2019Assignee: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10275454Abstract: According to an aspect, a term saliency model is trained to identify salient terms that provide supporting evidence of a candidate answer in a question answering computer system based on a training dataset. The question answering computer system can perform term saliency weighting of a candidate passage to identify one or more salient terms and term weights in the candidate passage based on the term saliency model. The one or more salient terms and term weights can be provided to at least one passage scorer of the question answering computer system to determine whether the candidate passage is justified as providing supporting evidence of the candidate answer.Type: GrantFiled: October 13, 2014Date of Patent: April 30, 2019Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Md Faisal Mahbub Chowdhury, Alfio M. Gliozzo, Adam Lally
-
Publication number: 20170371861Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: June 24, 2016Publication date: December 28, 2017Inventors: Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, David Ferrucci, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 9703861Abstract: System and method for providing answers to questions based on any corpus of data implements a method that generates a number of candidate passages from the corpus that answer an input query, and finds the correct resulting answer by collecting supporting evidence from the multiple passages. By analyzing all retrieved passages and that passage's metadata in parallel, an output plurality of data structures is generated including candidate answers based upon the analyzing. Then, supporting passage retrieval operations are performed upon the set of candidate answers, and for each candidate answer, the data corpus is traversed to find those passages having candidate answer in addition to query terms. All candidate answers are automatically scored by a plurality of scoring modules, each producing a module score. The modules scores are processed to determine one or more query answers; and, a query response is generated based on the one or more query answers.Type: GrantFiled: May 21, 2014Date of Patent: July 11, 2017Assignee: International Business Machines CorporationInventors: Eric W. Brown, David Ferrucci, Adam Lally, Wlodek W. Zadrozny
-
Publication number: 20140258286Abstract: System and method for providing answers to questions based on any corpus of data implements a method that generates a number of candidate passages from the corpus that answer an input query, and finds the correct resulting answer by collecting supporting evidence from the multiple passages. By analyzing all retrieved passages and that passage's metadata in parallel, an output plurality of data structures is generated including candidate answers based upon the analyzing. Then, supporting passage retrieval operations are performed upon the set of candidate answers, and for each candidate answer, the data corpus is traversed to find those passages having candidate answer in addition to query terms. All candidate answers are automatically scored by a plurality of scoring modules, each producing a module score. The modules scores are processed to determine one or more query answers; and, a query response is generated based on the one or more query answers.Type: ApplicationFiled: May 21, 2014Publication date: September 11, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, David Ferrucci, Adam Lally, Wlodek W. Zadrozny