Title:
MODEL TRAINING METHOD AND DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
Japanese Patent JP2023181109
Kind Code:
A
Abstract:
To reduce an influence caused by insufficient covering of a label word, and improve the performance of a preliminary training language model.SOLUTION: A model training method includes: a step 11 of acquiring a plurality of label words in different labels, and calculating the average vector of the label words for each of the labels to obtain a word average vector; a step 12 of inserting a masking text including a prediction word to be covered by masking into an input text to constitute a template for creating a prediction text; and a step 13 of training a preliminary training language model by using a first training sample, generating a word vector of the prediction word in a first prediction text by using the preliminary training language model, determining a prediction label of the first training sample based on the similarity between the word vector of the prediction word and the word average vector for each of the labels, and optimizing the preliminary training language model based on the prediction label of the first training sample and a labeled label.SELECTED DRAWING: Figure 1
More Like This:
Inventors:
LU LUO
DONG BIN
JIANG SHAN SHAN
REI DEIN
ZHANG YONG WEI
DONG BIN
JIANG SHAN SHAN
REI DEIN
ZHANG YONG WEI
Application Number:
JP2023089342A
Publication Date:
December 21, 2023
Filing Date:
May 31, 2023
Export Citation:
Assignee:
RICOH CO LTD
International Classes:
G06F40/216; G06N20/00
Attorney, Agent or Firm:
Tadashige Ito
Tadahiko Ito
Tadahiko Ito