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. 04, 2023

Filed:

Sep. 18, 2020
Applicant:

University of Electronic Science and Technology of China, Chengdu, CN;

Inventors:

Jianping Li, Chengdu, CN;

Xiaofeng Gu, Chengdu, CN;

Jian Hu, Chengdu, CN;

Ruinan Sun, Chengdu, CN;

Wenting Feng, Chengdu, CN;

Shunli Li, Chengdu, CN;

Sheng Jiang, Chengdu, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06F 40/289 (2020.01); G06F 40/216 (2020.01); G06F 17/16 (2006.01); G06K 9/62 (2022.01);
U.S. Cl.
CPC ...
G06F 40/289 (2020.01); G06F 17/16 (2013.01); G06F 40/216 (2020.01); G06F 40/30 (2020.01); G06K 9/6257 (2013.01);
Abstract

A method for machine reading comprehension includes: S, obtaining a character-level indication vector of a question and a character-level indication vector of an article; S, obtaining an encoded question vector and an encoded article vector; S, obtaining an output P1 of a bidirectional attention model and an output P2 of a shared attention model; S, obtaining an aggregated vector P3; S, obtaining a text encoding vector P4; S, obtaining global interaction information between words within the article; S, obtaining a text vector P5 after using the self-attention model; S, obtaining aggregated data P6 according to the text encoding vector P4 and the text vector P5; S, obtaining a context vector of the article according to the aggregated data P6 and an unencoded article vector P; and S, predicting an answer position according to the context vector of the article and the encoded question vector to complete the machine reading comprehension.


Find Patent Forward Citations

Loading…