Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Machine translation method and device and electronic equipment

A machine translation and sub-network technology, applied in the field of machine translation methods, devices and electronic equipment, can solve the problems of increasing prediction time and reducing machine translation efficiency, and achieve the effects of improving efficiency, reducing vocabulary, and shortening prediction time

Pending Publication Date: 2020-08-21
BEIJING KINGSOFT CLOUD NETWORK TECH CO LTD
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technical solutions, the machine translation network usually uses the traditional Softmax (logistic regression model) to obtain the probability output at the last layer. When dealing with a language structure similar to Chinese, due to the existence of a large number of words, it will increase the prediction time, reducing the efficiency of the entire machine translation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Machine translation method and device and electronic equipment
  • Machine translation method and device and electronic equipment
  • Machine translation method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. the embodiment. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0029] The terms "including" and "having" mentioned in the embodiments of the present application and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes other unlisted steps or units, or optionally...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides a machine translation method and device and electronic equipment, and relates to the technical field of cloud computing neural networks. The method comprises the steps that information to be translated is obtained, the information to be translated is information of a first language, the information to be translated is encoded into a first vector, then the first vector is predicted in a tree structure of a predetermined second language based on a binary classification method, a prediction result of the second language is obtained, wherein the tree structure comprises multiple words of the second language. The prediction result is determined through the binary classification method, the vocabulary amount can be reduced, the machine translation time isshortened, and the machine translation efficiency is improved.

Description

technical field [0001] The present invention relates to the technical field of cloud computing neural network, in particular to a machine translation method, device and electronic equipment. Background technique [0002] Transformer (machine translation structure) was first proposed in the paper "Attention is all you need" in 2017, and its performance on machine translation tasks surpassed that of Recurrent Neural Network (RNN) and Convolutional Neural Network (Convolutional Neural Network) Networks, CNN), which is of great significance to solve the problem of unparallelized training and long-term dependence of traditional RNN or CNN sequence models. The Transformer machine translation network is a model based on the Encoder-Decoder structure, which consists of encoding components, decoding components and connections between them. The encoding component part is composed of a bunch of encoders (encoders), and the decoding component part is also composed of the same number (c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/58G06F40/242G06N3/04G06N3/08G06K9/62
CPCG06F40/58G06F40/242G06N3/08G06N3/045G06F18/2415
Inventor 陈杰倪煜
Owner BEIJING KINGSOFT CLOUD NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com