logo

For the Inventor, By the Inventor

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.

Patent No.:

US 10832657 B1

PDFFull Text
Expired
Date of Patent:
Nov. 10, 2020

Filed:

Mar. 01, 2018

Use of small unit language model for training large unit language models

Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Masayuki Suzuki, Tokyo, JP;

Nobuyasu Itoh, Kanagawa, JP;

Gakuto Kurata, Tokyo, JP;

Assignee:

International Business Machines Corporation, Armonk, NY (US);

Attorneys:

Tutunjian & Bitetto, P.C.

Randall Bluestone

Primary Examiner:

Shaun Roberts

Int. Cl.
CPC ...
G10L 15/06 (2013.01); B41B 27/08 (2006.01); G10L 15/18 (2013.01); G10L 15/183 (2013.01); G10L 15/00 (2013.01); G06F 40/284 (2020.01); G06F 40/47 (2020.01); G06F 40/49 (2020.01); G06N 3/04 (2006.01);
U.S. Cl.
CPC ...
G10L 15/063 (2013.01); B41B 27/08 (2013.01); G06F 40/284 (2020.01); G06F 40/47 (2020.01); G06F 40/49 (2020.01); G10L 15/005 (2013.01); G10L 15/183 (2013.01); G10L 15/1815 (2013.01); G06N 3/0472 (2013.01);
Abstract

A computer-implemented method, computer program product, and apparatus are provided. The method includes generating a plurality of sequences of small unit tokens from a first language model that is trained with a small unit corpus including the small unit tokens, the small unit corpus having been derived by tokenization with a small unit. The method further includes tokenizing the plurality of sequences of small unit tokens by a large unit that is larger than the small unit, to create a derived large unit corpus including derived large unit tokens.

Find Patent Forward Citations

Quick Actions:

Suzuki, Masayuki. (2020). Use of small unit language model for training large unit language models (U.S. Patent No. 10832657). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/10832657

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…