Machine translation model obtaining method and device, text translation method and device and storage medium

A technology of machine translation and model acquisition, applied in computing models, machine learning, natural language translation, etc., can solve problems such as text recognition errors and inaccurate translation results, and achieve the effect of data enhancement, overcoming errors, and improving accuracy

Pending Publication Date: 2020-10-30
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The machine translation model is based on an end-to-end approach and is trained using a large-scale high-quality bilingual parallel corpus. It is assumed that the input text does not have lexical or grammati

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 model obtaining method and device, text translation method and device and storage medium
  • Machine translation model obtaining method and device, text translation method and device and storage medium
  • Machine translation model obtaining method and device, text translation method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0033] In addition, it should be understood that the term "and / or" in this article is only an association relationship describing associated objects, which means that there may be three relationships, for example, A and / or B may mean: A exists alone, and A exists at the same time. and B, there are three cases of B alone. In addition, the character " / " in this articl...

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 machine translation model obtaining method and device, a text translation method and device and a storage medium. The invention relates to the field of natural language processing and deep learning. The method can comprise the following steps: obtaining training data that includes training data composed of bilingual parallel corpora and training data composed of pseudo bilingual parallel corpora, wherein the bilingual parallel corpus comprises a real source language text and a corresponding real target language text, and the pseudo bilingual parallel corpus comprisesa real target language text and a source language text which is converted into pseudo data in a predetermined mode; and training a machine translation model by utilizing the training data so as to obtain a target language text corresponding to the source language text to be translated by utilizing the machine translation model, and wherein Pinyin embedding is added in the input of the machine translation model. By applying the scheme of the invention, the accuracy of the translation result and the like can be improved.

Description

technical field [0001] This application relates to computer application technology, in particular to methods, devices and storage media for machine translation model acquisition and text translation in the fields of natural language processing and deep learning. Background technique [0002] Simultaneous machine translation is an important application in the field of natural language processing. Its main implementation process is: convert speech into source language text through automatic speech recognition technology (ASR, Automatic Speech Recognition), and generate corresponding target language text through machine translation model . [0003] The machine translation model is based on an end-to-end approach and is trained using a large-scale high-quality bilingual parallel corpus. It is assumed that the input text does not have lexical or grammatical errors. However, in machine simultaneous translation, speech is first recognized as text After translation, there may be er...

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): G06F40/58G06F40/289G06N20/00
CPCG06F40/58G06F40/289G06N20/00
Inventor 刘继强张睿卿何中军李芝吴华
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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