The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 07, 2020

Filed:

Mar. 20, 2017
Applicant:

Elemental Cognition Llc, Wilton, CT (US);

Inventors:

David Ferrucci, Wilton, CT (US);

Mike Barborak, Fairfield, CT (US);

David Buchanan, Pleasantville, NY (US);

Greg Burnham, Brooklyn, NY (US);

Jennifer Chu-Carroll, Dobbs Ferry, NY (US);

Aditya Kalyanpur, Fort Lee, NJ (US);

Adam Lally, Stamford, CT (US);

Stefano Pacifico, New York, NY (US);

Chang Wang, White Plains, NY (US);

Assignee:

ELEMENTAL COGNITION LLC, Wilton, CT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/27 (2006.01); G06N 5/04 (2006.01); G06N 20/00 (2019.01); G06F 16/33 (2019.01);
U.S. Cl.
CPC ...
G06F 17/279 (2013.01); G06F 16/3331 (2019.01); G06F 17/271 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01);
Abstract

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.


Find Patent Forward Citations

Loading…