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

Neural machine translation method based on word prediction

A technology of machine translation and prediction mechanism, applied in the field of neural machine translation, which can solve the problems of inaccurate vocabulary translation, insufficient use of specific vocabulary information, and wrong translation of whole sentences.

Inactive Publication Date: 2017-11-24
NANJING UNIV
View PDF1 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current neural machine translation system, because the end-to-end serialization modeling of the entire sentence is only carried out, the specific vocabulary information cannot be fully utilized, resulting in inaccurate translation of certain words in the sentence, which may lead to the translation of the entire sentence wrong weakness,

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
  • Neural machine translation method based on word prediction
  • Neural machine translation method based on word prediction
  • Neural machine translation method based on word prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0150] This example compares the translation results of the basic neural machine translation model and the model using word prediction:

[0151] 1. Start translation work with basic neural machine translation models: "AOL, Time Warner's Internet company, said it expects advertising and commercial sales to drop from $2.7 billion in 2001 to $2.7 billion in 2002. One and a half billion dollars."

[0152] 2. The translation result of the basic neural machine translation model: "in the us line, the internet company's internet company said on the internet that it expected that the business sales in 2002 would fall from $UNK billion to $UNK billion in 2001.".

[0153] 3. The translation results of the neural machine translation model based on word prediction: "the internet company of timewarner inc., the us online, said that it expects that the advertising and commercial sales in 2002 will decrease from $UNK billion in 2001 to us$1.5billion.

[0154] 4. It can be clearly seen that t...

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 discloses a neural machine translation method based on word prediction. The method includes the step of adding a word prediction mechanism during the training process of an end-to-end neural machine translation system based on an attention mechanism, wherein the step can be specifically divided into two aspects: in the first aspect, the word prediction mechanism is added into a source end namely an encoding end; in the second aspect, the word prediction mechanism is added into a target end namely a decoding end. Compared with existing neural machine translation systems, the neural machine translation method based on the word prediction can fully utilize the information of words and enhance capabilities of the source end and the target end during training, so that the translation quality of the machine translation system can be improved, and during translation, by using the word prediction mechanism of the encoding end to compress a demanded word list, translation efficiency can be greatly improved. Under a practical experiment circumstance, the translation quality and efficiency can both be significantly improved.

Description

technical field [0001] The invention relates to a neural machine translation method based on word prediction. Background technique [0002] Neural machine translation has developed very rapidly in recent years and has made great progress, and has become a research hotspot in the field of machine translation. [0003] Although neural machine translation has made great progress, the practicability and usability of current machine translation are not very high, and the translation results for complex source language sentences are not ideal, especially the quality of machine translation between different language families It is urgent to improve. For large-scale online machine translation systems, translation efficiency is crucial. The structure based on the neural network means that compared with the traditional machine translation system, it needs to consume more computing resources, and the translation efficiency will be relatively reduced. How to improve translation quali...

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): G06F17/28G06F17/27G06N3/04
CPCG06F40/20G06F40/42G06N3/044
Inventor 黄书剑翁荣祥戴新宇陈家骏张建兵
Owner NANJING UNIV
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