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

Translation obtaining method and apparatus based on semantic forecast

An acquisition method and translation technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as failure to solve effective web pages, lack of research and processing, and difficulty in including effective web pages

Inactive Publication Date: 2007-09-26
FUJITSU LTD
View PDF0 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the top 100 pages hardly contain valid pages
[0007] According to the above analysis, the previous related researches all used the first 100 webpage summaries returned by general search engines to make statistics, and failed to solve the problem of how to obtain effective webpages with bilingual annotations
In addition, the previous studies basically used frequency features, and did not conduct in-depth research on other feature forms.

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 obtaining method and apparatus based on semantic forecast
  • Translation obtaining method and apparatus based on semantic forecast
  • Translation obtaining method and apparatus based on semantic forecast

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The specific implementation manner of the present invention will be described below in conjunction with the accompanying drawings. Fig. 1 shows a translation acquisition device based on semantic prediction according to an embodiment of the present invention. As shown in Fig. 1, in one embodiment, the device includes:

[0041] The unit segmentation device is divided into meaningful candidate unit sets by inputting the phrase unit (query item) as much as possible;

[0042] The unit translation knowledge base establishment device expands the unit candidate translations in the original general dictionary of the candidate unit through the method of extension and suffix semantic expansion (specifically, retains meaningful nouns or adjectives consisting of 1-3 words in the general dictionary, For multi-word entries, if they contain reserved options in the dictionary, their translations will be added to the translations of the options as their prefix and suffix semantic extensi...

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

This invention relates to one code message get method and device based on means prediction, which comprises the following steps: unit cutting step to divide the input requires into meanings prepare units set; unit codes knowledge database establishing to expend the prepare units in original common dictionary and to form unit code knowledge database; meaning prediction based on the prediction method to get relative times of the inquire meanings; effective page getting step to get the relative inquire items set by use of the combination times and to get effective page through index; prepare evaluating to get effective page to get prepare file list on codes.

Description

technical field [0001] The present invention relates to the field of computer information processing, in particular to the use of Web mining and machine learning algorithms for knowledge discovery. A method and device for obtaining a translation of the entity unit by semantic prediction in a target language. Background technique [0002] When people write in a foreign language, they usually encounter entity units (such as terms, proper nouns, phrases, and fixed phrases) that are not included in general dictionaries. , data retrieval, but still can not get an accurate translation result (for example: license plate number→License plate number, Romance of the Three Kingdoms→The Romance ofThree Kingdoms). In the machine translation system, there is often a lack of translation knowledge for unknown technical terms and nouns, which leads to a sharp decline in the translation accuracy of the entire system. In cross-language information retrieval, it is also because those query it...

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): G06F17/28G06F17/30
Inventor 方高林于浩
Owner FUJITSU 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

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