Title:
NEURAL NETWORK TRAINING METHOD
Document Type and Number:
WIPO Patent Application WO/2023/101364
Kind Code:
A1
Abstract:
A neural network training method according to an embodiment comprises the steps of: training a first neural network on the basis of first input data; training a second neural network on the basis of second input data by applying a parameter value of the first neural network according to a training result of the first neural network; and training a third neural network on the basis of third input data by applying the parameter value of the first neural network, wherein the first input data includes a patent domain document, the second input data includes multiple patent documents and first label data obtained by labeling key sentences corresponding to the respective multiple patent documents, and the third input data includes multiple key sentences and second label data obtained by labeling key noun phrases respectively corresponding to the multiple key sentences.
More Like This:
Inventors:
JUNG WON KYUNG (KR)
MOON HYEON SEOK (KR)
PARK CHAN JUN (KR)
SON JUN YOUNG (KR)
LEE SEOL HWA (KR)
LEE JEONG WOO (KR)
LIM HEUI SEOK (KR)
MOON HYEON SEOK (KR)
PARK CHAN JUN (KR)
SON JUN YOUNG (KR)
LEE SEOL HWA (KR)
LEE JEONG WOO (KR)
LIM HEUI SEOK (KR)
Application Number:
PCT/KR2022/019082
Publication Date:
June 08, 2023
Filing Date:
November 29, 2022
Export Citation:
Assignee:
LG INNOTEK CO LTD (KR)
International Classes:
G06N3/08; G06F16/34; G06F40/205; G06F40/258; G06F40/289; G06N3/04
Foreign References:
| KR20210125588A | 2021-10-18 | |||
| KR20200106108A | 2020-09-11 | |||
| KR20180097120A | 2018-08-30 | |||
| KR102225822B1 | 2021-03-10 | |||
| US10713443B1 | 2020-07-14 |
Attorney, Agent or Firm:
HAW, Yong Noke (KR)
Download PDF: