Title:
METHOD AND APPARATUS FOR JOINTLY TRAINING NATURAL LANGUAGE PROCESSING MODEL ON BASIS OF PRIVACY PROTECTION
Document Type and Number:
WIPO Patent Application WO/2023/109294
Kind Code:
A1
Abstract:
Embodiments of the present application provide a method for jointly training a natural language processing (NLP) model on the basis of privacy protection, wherein the NLP model comprises a coding network located at a first party and a processing network located at a second party. According to the method, after the first party obtains a local target training statement, the target training statement is inputted into the coding network, and a sentence representation vector is formed on the basis of coding output of the coding network. Then, target noise conforming to differential privacy is added to the sentence representation vector to obtain a target noise adding representation. The target noise adding representation is sent to the second party for training of the processing network.
More Like This:
Inventors:
DU JIAN (CN)
MO FENGRAN (CN)
WANG LEI (CN)
MO FENGRAN (CN)
WANG LEI (CN)
Application Number:
PCT/CN2022/125464
Publication Date:
June 22, 2023
Filing Date:
October 14, 2022
Export Citation:
Assignee:
ALIPAY HANGZHOU INF TECH CO LTD (CN)
International Classes:
G06F21/62; G06F40/20; G06N3/04
Foreign References:
| CN113961967A | 2022-01-21 | |||
| CN112101946A | 2020-12-18 | |||
| CN113282960A | 2021-08-20 | |||
| CN113642717A | 2021-11-12 | |||
| US20210342546A1 | 2021-11-04 | |||
| US20210216902A1 | 2021-07-15 |
Attorney, Agent or Firm:
E-TONE INTELLECTUAL PROPERTY FIRM (GENERAL PARTNERSHIP) (CN)
Download PDF: