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

A method and device for translating Chinese-English institution names with the aid of network knowledge

A technology of knowledge assistance and institution name, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve the problems of increasing the difficulty of translation of institution names, affecting the results of alignment and translation, and unable to guarantee the correct rate of word segmentation, etc. , to avoid errors, improve accuracy, and avoid structural problems

Inactive Publication Date: 2011-12-07
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) Difficulty in word segmentation: Because the transliteration or abbreviation is often an unregistered word, the accuracy of word segmentation cannot be guaranteed, which affects the results of alignment and translation;
[0006] (2) The structure is complex: because the name of the organization can include the names of sub-organizations, the complex structure increases the difficulty of translation of the name of the organization;
[0007] (3) Order problem: the order of the words in the translation results is very random, and it is difficult to describe with specific rules. For example, "Bank of China" needs to be translated as "the bank of china", and "Citibank" is translated as "the city bank";
[0008] (4) word selection problem: that is, it is necessary to choose the most suitable one among English words with similar meanings

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 method and device for translating Chinese-English institution names with the aid of network knowledge
  • A method and device for translating Chinese-English institution names with the aid of network knowledge
  • A method and device for translating Chinese-English institution names with the aid of network knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The method of the present invention will be further described in detail below with reference to the description of the drawings and specific embodiments. It should be noted that the described embodiments are only intended to facilitate the understanding of the present invention, and have no limiting effect on it.

[0024] In order to solve the four difficulties in the translation of Chinese-English organization names, the present invention directly extracts the target translation from the webpage by using some clues provided by the statistical translation module 1 with the help of network resources.

[0025] Such as figure 1 As shown in the flow chart of the translation of Chinese-English institution names assisted by network mining in the present invention, the premise of the present invention to assist the translation of Chinese-English institution names by means of network mining methods is that an effective query can be constructed first, and secondly that the query ...

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 method and device for translating Chinese-English organization names. The Chinese organization names to be translated are divided into four language blocks using a word-based conditional random field model, and word segmentation is performed on the four language blocks. Select words with a certain amount of information and translation confidence for statistical translation, get the translation results of several words in the organization name, and form a bilingual query with the Chinese organization name to be translated. Retrieve the query with the help of a search engine, and obtain several fragments of bilingual webpages in both Chinese and English. Extract the English in the webpage fragments, and use the Chinese-English asymmetric alignment technology to screen the fragments in the English sentences that have the highest probability of being aligned with the Chinese organization name. By counting information such as the frequency of occurrence of each segment, an optimal segment is determined as the translation of the Chinese institution name. This method overcomes the structure, sequence and word selection errors that the statistical translation model tends to produce in the translation process of institution names, and the accuracy rate of institution name translation is increased by 35.26%.

Description

technical field [0001] The invention relates to the technical field of natural language processing, and relates to a method and device for assisting the translation of Chinese-English organization names by means of network mining. Background technique [0002] Named entities include seven categories such as person names, place names, and organization names. Named entities convey important information in human language, and its recognition is one of the key technologies in the field of natural language processing. In multilingual processing, the translation results of named entities directly affect the performance of multilingual information processing application systems. Organization name is the most important and complex category of named entities, so the translation of organization names is also a difficult point in the translation of named entities. Due to the universality, importance and complexity of institution names, the study on the translation of Chinese-English ...

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 Patents(China)
IPC IPC(8): G06F17/28G06F17/30
Inventor 赵军杨帆
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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