US 11,687,734 B2
Systems and methods to extract the context of scientific measurements using targeted question answering
Corey A. Harper, Brooklyn, NY (US); Jessica Rose Cox, Williston Park, NY (US); Antony Jason Scerri, Worcester Park (GB); and Ronald E. Daniel, Jr., Concord, CA (US)
Assigned to ELSEVIER, INC., New York, NY (US)
Filed by Elsevier, Inc, New York, NY (US)
Filed on Jul. 2, 2020, as Appl. No. 16/919,713.
Claims priority of provisional application 62/870,951, filed on Jul. 5, 2019.
Prior Publication US 2021/0004540 A1, Jan. 7, 2021
Int. Cl. G06F 40/40 (2020.01); G06F 16/332 (2019.01); G06F 16/33 (2019.01); G06F 16/31 (2019.01)
CPC G06F 40/40 (2020.01) [G06F 16/313 (2019.01); G06F 16/3329 (2019.01); G06F 16/3344 (2019.01); G06F 16/3347 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a computing device, an electronic document;
identifying a numerical value in the document;
extracting the numerical value and a portion of text surrounding the numerical value from the document to obtain extracted text;
inputting the extracted text into a trained neural network to create a vector representation of the extracted text;
generating a series of questions associated with the extracted text;
generating answers to the series of questions based on the vector representation of the extracted text;
determining a context associated with the numerical value based on the answers to the series of questions; and
storing the numerical value and the context associated with the numerical value in a database.