Unlock instant, AI-driven research and patent intelligence for your innovation.

Machine translation method and device and medium

A technology of machine translation and translation model, applied in the field of neural machine translation, can solve the problems of not so good effect and lack of pertinence

Active Publication Date: 2020-07-14
BEIJING XIAOMI PINECONE ELECTRONICS CO LTD
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such a construction method is not targeted. Most of the correct corpus does not need to add pinyin information. Adding pinyin information will make the translation of the correct corpus not so good.

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 method and device and medium
  • Machine translation method and device and medium
  • Machine translation method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.

[0090] At present, language translation mainly adopts the cascading mode of first speech recognition and then machine translation, and performs translation for the speech translation scene with Chinese as the source language. In this way, errors in homophones may occur during speech recognition, including errors in which the pinyin and the tone are completely consistent, and errors in which the ...

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 machine translation method and device and a medium. The method comprises: obtaining a to-be-translated source language sequence, wherein the source language sequence is a Chinese character sequence; based on the Chinese character sequence and a trained discrimination model, obtaining a processed source language sequence, the discrimination model being used for discriminating whether a Chinese character in the Chinese character sequence is replaced with a corresponding pinyin; and inputting the processed source language sequence into a trained translation model to obtain a prediction result of the trained translation model. According to the method, the robustness of the translation model can be improved, so that the neural machine translation quality is effectively enhanced.

Description

technical field [0001] The present disclosure relates to the technical field of neural machine translation, in particular to a machine translation method, device and medium. Background technique [0002] Neural machine translation is currently the most mainstream machine translation method. Although the translation quality has been greatly improved, it is very sensitive to the input text to be translated. Even if there are a small number of errors in the source language that do not affect human understanding of semantics, the model generally cannot generate correct translation. The methods to enhance the robustness of neural machine translation mainly include: (1) correcting the Chinese input text to improve the quality of subsequent machine translation; (2) improving the training method of the neural machine translation model and enhancing the model’s resistance to noisy training samples. Noise, improve the robustness of the translation model. [0003] A common type of 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/58G06F40/284G06N3/08
CPCG06N3/08
Inventor 孙于惠李响
Owner BEIJING XIAOMI PINECONE ELECTRONICS CO LTD