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

Neural machine translation model training method and neural machine translation method and device

A technology of machine translation and translation model, applied in the field of machine translation, can solve the problem of inaccurate translation of words outside the set, and achieve the effect of improving translation accuracy

Pending Publication Date: 2020-08-14
THE BOEING CO +1
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The embodiment of the present invention provides a neural machine translation model training method, neural machine translation method and device, to at least solve the problem that out-of-set words cannot be accurately translated in the process of 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
  • Neural machine translation model training method and neural machine translation method and device
  • Neural machine translation model training method and neural machine translation method and device
  • Neural machine translation model training method and neural machine translation method and device

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0147] Step 4: Train a neural machine translation model based on the label-replaced training data, so that the translation model can receive the input of the translated sentence with the PER label and output the target translation sentence with the corresponding position label. The specific implementation is as follows:

[0148] The open source seq2seq neural machine translation model transformer based on the self-attention mechanism can be used to train the tagged sentence translation model. Translation models are available for free download at:

[0149] https: / / github.com / tensorflow / tensor2tensor

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 neural machine translation model training method and a neural machine translation method and device. The neural machine translation method comprises: identifying a named entity in a to-be-translated source statement; replacing the identified named entity with a label corresponding to the category of the named entity to obtain an intermediate source statement; translatingthe intermediate source statement through a neural machine translation model to obtain an intermediate target statement with a label; searching translations of the named entities from a preset namedentity dictionary and / or named entity library; and replacing the corresponding label in the intermediate target statement with the found translation to obtain a target statement corresponding to the source statement to be translated. The problem that the low-frequency named entity is wrongly translated or missed in the machine translation process is solved.

Description

technical field [0001] The present invention relates to the field of machine translation. Specifically, the present invention relates to a neural machine translation model training method and device, a neural machine translation method and device, a storage medium and a processor. Background technique [0002] Machine translation is one of the important research directions in the field of artificial intelligence. After experiencing the development period of traditional rule-based machine translation (RBMT) and statistical machine translation (SMT), it is now ushering in the development of neural machine translation (NMT). Mainstream new translation model boom. Neural machine translation directly uses the neural network to perform translation modeling in an end-to-end (End-to-End) manner, and uses the neural network to learn translation features to directly map the source language into the target language text. [0003] Although neural machine translation has excellent perf...

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): G06F40/58G06F40/56G06F40/295G06F40/242
Inventor 张家俊周玉闫璟辉宗成庆杨里
Owner THE BOEING CO
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