Mongolian and Chinese inter-translation method based on reinforced learning

A reinforcement learning, bilingual technology, applied in natural language translation, special data processing applications, instruments, etc., can solve the problems of insufficient bilingual alignment corpus, scarce resources, high cost of obtaining parallel corpora, and achieve the effect of solving the problem of insufficient bilingual alignment corpus

Active Publication Date: 2018-11-30
INNER MONGOLIA UNIV OF TECH
View PDF8 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the field of minority language translation, such translation tasks generally face difficulties such as insufficient bilingual alignment corpus, scarce resources,

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
  • Mongolian and Chinese inter-translation method based on reinforced learning
  • Mongolian and Chinese inter-translation method based on reinforced learning
  • Mongolian and Chinese inter-translation method based on reinforced learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0047] The present invention is a Mongolian-Chinese bilingual neural translation method based on reinforcement learning, which adopts an encoding-decoding structure to fine-tune the NMT model. The training process of fine-tuning only pays attention to the relevant sentences, and at the same time, the reinforcement learning feedback mechanism is used to accept a source language sentence for translation. Translate, generate a sentence in the target language, and get a scalar score as feedback, using reinforcement learning techniques to learn effectively from the feedback.

[0048] Specifically, the present invention uses the reinforcement learning strategy gradient method to train the Mongolian-Chinese translation model, hoping to improve the strategy to maximize long-term returns, but unlabeled samples will not tell which action b is corre...

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

Nerve machine translation (NMT) of a coder-decoder architecture realizes an optimal result on current standard machine translation standards, but a lot of parallel corpus data are needed for traininga model; for the field of minority language translation, insufficient bilingual alignment corpus is a common problem, and resources are rare, so that the invention provides a Mongolian and Chinese inter-translation method based on reinforced learning. A system receives a Mongolian sentence and translates the same to generate a Chinese sentence, and a scalar score is acquired as feedback. Reinforced learning technology is utilized for effective learning from the feedback. Defining a mathematical framework of a solution in reinforced learning is called the Markov decision-making process. It is aimed to find a strategy to maximize expected translation quality. During training, if a certain behavior strategy causes a big environment reward, tendency of generating this behavior strategy in thefuture is about to be reinforced, and an optimal strategy is found finally to maximize expected discount reward sum and improve translation quality.

Description

technical field [0001] The invention belongs to the technical field of machine learning, in particular to a Mongolian-Chinese bilingual translation method based on reinforcement learning. Background technique [0002] With the widespread application of the Internet, the acceleration of the process of world economic integration and the increasing frequency of international exchanges, machine translation technology plays an increasingly important role in promoting political, economic, and cultural exchanges. [0003] Under the background of my country's rapid economic development and continuous social progress, the communication between Mongolians and Han people is becoming more and more frequent, and Mongolian is the main language used by Mongolian compatriots in my country, and Mongolian is the official language of Mongolia, so Mongolian The study of Chinese machine translation is of great significance for the mutual penetration of the values ​​of the two cultures, the cohesi...

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
IPC IPC(8): G06F17/28
CPCG06F40/42G06F40/58
Inventor 苏依拉高芬张振王宇飞孙晓骞牛向华赵亚平
Owner INNER MONGOLIA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap