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:
Dec. 24, 2024

Filed:

Aug. 22, 2022
Applicants:

Tianxiong Xiao, Beijing, CN;

Rui Cheng, Beijing, CN;

Bin Dong, Beijing, CN;

Shanshan Jiang, Beijing, CN;

Jiashi Zhang, Beijing, CN;

Inventors:

Tianxiong Xiao, Beijing, CN;

Rui Cheng, Beijing, CN;

Bin Dong, Beijing, CN;

Shanshan Jiang, Beijing, CN;

Jiashi Zhang, Beijing, CN;

Assignee:

Ricoh Company, Ltd., Tokyo, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/30 (2020.01); G06F 16/33 (2019.01); G06F 16/332 (2019.01); G06F 40/205 (2020.01); G06F 40/40 (2020.01); G06F 40/47 (2020.01); G06F 40/56 (2020.01); G06N 3/0455 (2023.01); G06N 5/02 (2023.01); G06N 7/00 (2023.01);
U.S. Cl.
CPC ...
G06F 40/47 (2020.01); G06F 16/33 (2019.01); G06F 16/3329 (2019.01); G06F 16/3334 (2019.01); G06F 40/205 (2020.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01); G06F 40/56 (2020.01); G06N 3/0455 (2023.01); G06N 5/02 (2013.01); G06N 7/00 (2013.01);
Abstract

A method and an apparatus for machine reading comprehension, and a non-transitory computer-readable recording medium are provided. In the method, a paragraph-question pair is obtained, and subword vectors corresponding to subwords in the paragraph-question pair are generated. Then, for each subword, relative positions of the subword with respect to the other subwords are determined based on distances, and self-attention information of the subword in a first part and mutual attention information of the subword in a second part are calculated by using the relative positions and the subword vector. Then, a fusion vector of the subword is generated based on the self-attention information and the mutual attention information. Then, the fusion vectors of the subwords are input to a decoder of a machine reading comprehension model so as to obtain an answer predicted by the decoder.


Find Patent Forward Citations

Loading…