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

Translation method and device

A technology of translation results and translation models, applied in natural language translation and other directions, can solve the problems of high labor and time costs, and the inability to optimize the translation quality of translation models, and achieve the effect of reducing labor and time costs.

Pending Publication Date: 2022-01-18
ALIBABA GRP HLDG LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires manual collection of mistranslated sentences and correction of mistranslated sentences, which has high manpower and time costs, and mistranslated sentences can only be collected after the translation model is applied online, and the translation model cannot be optimized before the translation model is applied online translation quality of

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
  • Translation method and device
  • Translation method and device
  • Translation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0023] Aiming at the problems existing in the prior art, the present invention provides a translation method and device to automatically improve the accuracy of the translation model and avoid wasting manpower and time costs.

[0024] The translation method of the present invention is used to optimize the first translation model to generate a second translation model with higher translation accuracy. After the second translation mo...

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 translation method. The method comprises the following steps: taking a source language statement and a target language statement corresponding to the source language statement as training samples, and training to generate a first translation model; inputting the source language statement into a first translation model to obtain a translation result of the source language statement; comparing the translation result with a corresponding target language statement to determine a mistranslation fragment in the translation result and a corresponding mistranslation source fragment; and training the first translation model to generate a second translation model by taking the source language statement containing the mistranslation source fragment and the target language statement corresponding to the source language statement as training samples and taking reduction of the generation probability of the mistranslation fragment as a training target. The invention also discloses a corresponding device.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a translation method and device. Background technique [0002] The current neural machine translation (Neural Machine Translation, NMT) system can translate sentences similar to human language, but the current neural machine translation model training method pays more attention to the overall quality of the generated translation sentences, making the sentences translated by the model very difficult. Fluency, low accuracy, and frequent mistranslations, that is, the semantics of the translation result deviates from the semantics of the input sentence to be translated. [0003] In order to improve the accuracy of the translation model, the current common practice is to collect mistranslated sentences during the application process of the translation model, manually correct the mistranslated sentences, and then add the corrected sentences to the training s...

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): G06F40/56G06F40/44G06F40/58
CPCG06F40/56G06F40/58G06F40/44
Inventor 翁荣祥于恒骆卫华
Owner ALIBABA GRP HLDG LTD
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