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

Method and device for translating text information, and terminal device

A text information and text technology, applied in natural language translation, special data processing applications, instruments, etc., can solve the problem of low translation accuracy, achieve strong topic description characteristics, and improve translation accuracy

Active Publication Date: 2018-11-20
INST OF SCI & TECHN INFORMATION OF CHINA
View PDF11 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing machine translation methods have improved the translation quality to some extent, there are still problems of low translation accuracy in the process of translating translated texts, such as foreign language scientific and technological texts.

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
  • Method and device for translating text information, and terminal device
  • Method and device for translating text information, and terminal device
  • Method and device for translating text information, and terminal device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The embodiment of the application provides a method for translating text information, such as figure 1 Shown, including:

[0033] Step S100: parse the text information to be translated, and determine the subject text and format information of the text information to be translated.

[0034] Specifically, the text to be translated in this embodiment can be the text of a dissertation, or a patent, of course, it can also be a text in other record forms. Among them, the text of thesis and the patent text mainly refer to scientific and technological texts that record scientific research activities and research methods. , That is, the text to be translated in this embodiment mainly refers to the text of a scientific paper or a scientific patent text. The scientific text can be saved in PDF format, word format, or other existing saving methods, such as .txt format , This application does not restrict it.

[0035] Further, in this embodiment, the text information to be translated is a...

Embodiment 2

[0044] The embodiment of the present application provides another possible implementation manner. On the basis of the first embodiment, it also includes the method shown in the second embodiment, wherein:

[0045] Step S100 includes step S1001 (not marked in the figure), step S1002 (not marked in the figure), step S1003 (not marked in the figure), and step S1004 (not marked in the figure), in which,

[0046] Step S1001: Determine the full-text characters of the text information to be translated and the position information of each character, and perform word division and line-combination on the full-text characters according to the position information of each character to obtain corresponding line fragments.

[0047] Step S1002: Determine the number of line segments whose length difference is less than a preset length threshold.

[0048] Step S1003: Combine the line segments into corresponding paragraphs according to the topological structure of the line segments, and record the posit...

Embodiment 3

[0057] The embodiment of the present application provides another possible implementation manner. On the basis of the first and second embodiments, it also includes the method shown in the third embodiment, wherein:

[0058] Step S200 includes step S2001 (not marked in the figure) and step S2002 (not marked in the figure). Among them,

[0059] Step S2001: According to the pre-established document content organization framework template, the subject text and the layout information are divided into content modules to obtain multiple subject frames of the text information to be translated.

[0060] Step S2002: Based on the preset theme unit expression mode and multiple theme frames, at least one theme element included in each theme frame is determined through regular pattern matching.

[0061] Specifically, when step S200 specifically determines multiple theme frames of the text information to be translated based on the theme text and format information, step S200 only needs to include st...

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 present invention relates to the field of natural language processing and discloses a method and device for translating text information, a terminal device and a computer-readable storage medium.The method for translating the text information comprises: analyzing the text information to be translated to determine a subject text and format information of the text information to be translated;determining a plurality of subject frames of the text information to be translated or at least one subject element in each subject frame on the basis of the subject text and the format information; and performing sub-topic frame translation or sub-topic element translation on the subject text by using a trained translation model corresponding to each subject frame or each subject element. The method of the embodiment of the present application realizes the more fine-grained content extraction of the text information to be translated, can realize the targeted translation of the sub-topic framesor sub-topic elements of the text to be translated, so that the translation result has a clear subject and strong topic description characteristics, and the translation accuracy is improved.

Description

Technical field [0001] This application relates to the field of natural language processing technology. Specifically, this application relates to a method, device, terminal device, and computer-readable storage medium for text information translation. Background technique [0002] Text refers to the use of written language to record an event. It can be divided into scientific and technological texts, documentary texts, and narrative texts. Among them, scientific texts are an important carrier for recording scientific research activities and research methods. The personnel obtain scientific and technological experience and understand the main literature of the industry's cutting-edge technology. At present, a large number of scientific and technological texts are presented in English, Japanese, German, French, and medium languages. Faced with a large number of scientific and technological text resources, it is more and more difficult to rely on human resources to understand the la...

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): G06F17/28
CPCG06F40/55G06F40/58
Inventor 石崇德何彦青许德山
Owner INST OF SCI & TECHN INFORMATION OF CHINA
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