A term translation method and device

A technology of terms and term bases, applied in the field of language translation, can solve the problems that neural network machine translation cannot reach translators well, and neural network machine translation cannot be added to term bases, etc.

Pending Publication Date: 2019-06-18
GLOBAL TONE COMM TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) Existing technologies cannot add terminology databases to neural network machine translation and specify explanations for corresponding terms
[0008] (2) Terminology translation problems are often encountered in human translation, and neural network machine translation cannot meet the expectations of translators well

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
  • A term translation method and device
  • A term translation method and device
  • A term translation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] like figure 2 , such as entering the text to be translated is Who is eric?

[0052] Through machine translation to output the alignment information of the translation, we can get the above figure 2 As shown in the results, assuming that Eric is interpreted as Yu Zong in the term base, the following results can be obtained through the search of the term base and the corresponding alignment information: as image 3 .

[0053] For insufficient alignment information, the alignment information corresponding to the term cannot be found, and the following methods can be used:

[0054] In neural network machine translation, a class of unregistered words is predefined as UNK+serial number, such as UNK1, UNK2...UNK9.

[0055] Use the unknown word mark UNK+serial number to mark the original text, and send it to the neural network machine translation system. Since there are unregistered words in the translation of the neural network machine translation, the word will not be tr...

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 belongs to the technical field of language translation, and discloses a term translation method and device, and the method comprises the steps: converting a term library into dictionaries in key and value forms, and storing the dictionaries in a database; Inputting the normal to-be-translated text into a machine translation terminal, and automatically generating a translated text andcorresponding text alignment information through machine translation; And according to the alignment information, replacing the corresponding term with a specified explanation. According to the method, machine translation and term translation in manual translation are combined, so that more results summarized by human experience are received by machine translation, the translation quality is further improved, and the expectation of translation workers is achieved; According to the method, the user can be allowed to use the pre-defined term library in the using process and apply the term library to machine translation, so that the term translation in the machine translation better conforms to the expected effect.

Description

technical field [0001] The invention belongs to the technical field of language translation, and in particular relates to a term translation method and device. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] The current neural network machine translation has greatly improved the quality of machine translation compared with statistical machine translation. However, due to the black-box characteristics of the neural network machine translation translation model, all translation intermediate processes are not interpretable, and the network is artificially modified. The possibility of parameters is almost zero. Therefore, for the term translation problems often encountered in human translation, neural network machine translation cannot do this job very well. [0004] Terminology translation is aimed at a given term base, and when a term exists in the term base is encountered during the translation proce...

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): G06F17/28
Inventor 宗浩程国艮
Owner GLOBAL TONE COMM TECH
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