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

Language translation quality auditing method

A language translation and quality technology, applied in the field of language translation quality audit, can solve the problems of difficulty in guaranteeing translation and audit quality and consuming human resources.

Inactive Publication Date: 2010-12-22
陈洁
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this manual translation and review method not only consumes a lot of human resources, but also makes it difficult to guarantee the quality of translation and review

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
  • Language translation quality auditing method
  • Language translation quality auditing method
  • Language translation quality auditing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Based on the above design ideas, refer to figure 1 The flow chart of the auditing method of the present invention shown, the concrete steps of the language translation quality auditing method designed by the present invention are as follows:

[0067] (1) Mark category marks for all source and target languages;

[0068] Here, the so-called source language refers to the original article to be translated, and the so-called target language refers to the translated article to be reviewed.

[0069] As mentioned above, the semantic difference degree comparison between sentences in the present invention is based on the category identification in the category grammar as the structural basis. The so-called categorical grammar is a syntactic type calculus proposed by the mathematician J. Lambek in "The Mathematics of Sentence Structure" in 1958. It is a calculus theory that uses different symbols to represent each component in a sentence, and then uses the symbol string to ident...

Embodiment 2

[0089] In this embodiment, on the basis of Embodiment 1, the sentence pairing method in the step (4) is further limited. Such as figure 2 As shown, the step (4) includes the following specific steps:

[0090] (41) Calculate the semantic difference A of each sentence of the target language relative to each sentence of the reference sentence in turn according to the calculation formula of the degree of semantic difference 1 ; The formula for calculating the degree of semantic difference is A 1 (Sn, S'm) = ΣC XSn *δ XSn *DD X (Sn, S'm);

[0091] Among them, A 1 (Sn, S'm) indicates the degree of semantic difference between the Snth sentence in the target language and the S'mth sentence in the reference sentence, DD X (Sn, S'm) represents the range of lexical semantic change between the Snth sentence in the target language and the Xth pair of category labels in the S'mth sentence in the reference sentence, δ XSn Indicates the importance weight value of the category identif...

Embodiment 3

[0104] This embodiment further limits the generation process of the reference sentence in the step (3) on the basis of the first embodiment. The reference sentence generation process of described step (3) is specifically as follows:

[0105] (3) The source language is directly replaced with vocabulary based on the dictionary based on the category identification marked in step (1), thereby generating a reference sentence.

[0106] Here, the source language performs direct replacement of words or phrases with the minimum set of category labels. If a synonym or near-synonym is encountered, a group of synonyms or near-synonym are directly replaced for the category identifier at the same time. As mentioned above, the reference sentence generated here is only used as a reference basis for comparing the target language and each translation sentence in the translation comparison library, so it is not necessary to refer to any language grammar rules during the generation process, as l...

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 provides a language translation quality auditing method. The method comprises the following steps of: translating a translated parent language to form a translation comparison library based on numerous conventional reliable translation methods; respectively performing a semantic comparison which takes category identification as a base structure on each translation sentence and each target language to be audited in the translation comparison library with a reference sentence generated according to the parent language; calculating a corresponding semantic difference degree; judging whether the semantic difference degree between the target language and the reference sentence is in the range of the semantic difference degree between each translation sentence and the reference sentence in the translation comparison library and then judging whether the translation is reliable; and proving modification for mistranslation. The auditing method has high automation and standardization degrees and is an ideal translation quality auditing method.

Description

technical field [0001] The invention relates to a language translation quality review method, in particular to a computer program-based automatic and standardized language review method for reviewing and evaluating the language translation quality, and even modifying it, belonging to the technical fields of linguistics and computer science. Background technique [0002] At present, there are various methods for machine translation, among which the skeleton dependency tree and block group methods are more commonly used. Their core is to decompose the sentence structure and calculate the semantic similarity. The difference is that the structural unit of the former is a whole composed of the predicate head word and its dominant components, while the latter is a functional language block, such as a subject block and a predicate block. [0003] The target language output by machine translation is the semantic correspondence based on the skeleton or chunk structure of the source ...

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): G06F17/28G06F17/27
Inventor 陈洁
Owner 陈洁
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