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

Word forecasting method and system based on nerve machine translation system

A technology of machine translation and prediction method, applied in neural architecture, natural language translation, biological neural network model, etc., can solve problems such as poor word prediction probability

Active Publication Date: 2017-06-13
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the word prediction probability obtained by the neural translation model is relatively poor, the present invention provides a word prediction method and system based on a neural machine translation system

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
  • Word forecasting method and system based on nerve machine translation system
  • Word forecasting method and system based on nerve machine translation system
  • Word forecasting method and system based on nerve machine translation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.

[0063] Such as figure 1 Shown, the word prediction method of the present invention based on neural machine translation system comprises:

[0064] Step 100: use the statistical machine translation system to train the parallel corpus, extract from the training results, and obtain the phrase translation table;

[0065] Step 200: Based on the phrase translation table, perform a matching search on the source language sentences in any parallel sentence pair, and determine all the source language phrases contained in the source language sentences;

[0066] Step 300: Based on each of the source language phrases, look up target phrase translation can...

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 invention relates to a word forecasting method and system based on a nerve machine translation system. The word forecasting method includes the steps that parallel corpora are trained, extracting is carried out from the training result, and a phrase translation table is obtained; source language sentences in any parallel sentence pairs are subjected to matching searching, and all source language phrases contained in the source language sentences are determined; target phrase translation candidate sets corresponding to all the source language phrases respectively are found from the phrase translation table; part of obtained translations are translated according to the target phrase translation candidate sets and the nerve machine translation system, and target word sets needing to be encouraged are obtained; encouragement values of all target words in the target word sets are determined according to the attention probability and the target phrase translation candidate sets which are based on the nerve machine translation system; the prediction probability of all the target words is obtained according to the encouragement values of all the target words. The encouragement values of the target words are obtained in the mode that the phrase translation table is introduced and added into a nerve translation model, and therefore the prediction probability of the target words can be increased.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, and more specifically, to a word prediction method and system based on a neural machine translation system. Background technique [0002] Machine translation is the use of computers to convert between different languages. The translated language is usually called the source language, and the resulting language translated into is called the target language. Machine translation is the process of converting from a source language to a target language. [0003] Neural machine translation is the latest machine translation method that has emerged in recent years. It has a significant improvement in translation quality compared with the original statistical machine translation method. Compared with previous statistical machine translation methods, neural machine translation requires less engineering design and translates better. When it was first proposed, it achieved accu...

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): G06F17/28G06F17/27G06N3/04
CPCG06F40/284G06F40/58G06N3/04
Inventor 张家俊赵阳王亦宁宗成庆
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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