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

Pivot language translation method and device based on similarity matching

A technology of similarity matching and pivot language, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve problems such as loss of translation rules

Active Publication Date: 2014-02-26
严格集团股份有限公司
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention solves the problem that the existing translation method and device require the translation rules from the source language to the pivot language and the translation rules from the pivot language to the target language in the construction of the source language-target language translation rule base, that is, in rule 1 and rule 2 The potential translation rule loss problem caused by the pivot language phrases must be exactly the same, and a pivot language translation method and device based on similarity matching is proposed

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
  • Pivot language translation method and device based on similarity matching
  • Pivot language translation method and device based on similarity matching
  • Pivot language translation method and device based on similarity matching

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Embodiment 1: In this embodiment, a pivot language translation method based on similarity matching is specifically carried out in accordance with the following steps:

[0030] Step 1. Establishing a source language-target language translation rule base, which specifically includes the following steps:

[0031] Step 11, establishing the source language-pivot language translation rule base, in the source language-pivot language translation rule base, the pivot language phrase is represented as a vector form;

[0032] Step 12, establish the pivot language-target language translation rule base, in the pivot language-target language translation rule base, express the pivot language phrase as a vector form;

[0033] Step 13, searching the vector representation of at least one first pivot phrase semantically matching the source language phrase in the source language-pivot language translation rule base;

[0034] Step 14. Search the vector representation of at least one second...

specific Embodiment approach 2

[0038] Embodiment 2: In this embodiment, a pivot language translation device based on similarity matching, the device includes:

[0039] 1. The pivot language phrase vector representation module 410 is used to represent the pivot language phrase as a vector in the source language-pivot language translation rule base and convert the pivot language phrase into a vector form in the pivot language-target language translation rule base. Expressed in vector form;

[0040] 2. The pivot language phrase search module 420, whose function is to: search the vector representation of at least one first pivot language phrase that matches the semantics of the first source language phrase in the source language-pivot language translation rule base;

[0041] 3. The vector similarity calculation module 430 is used to calculate the semantic similarity between the pivot phrase in the pivot language-target language translation rule base and the first pivot phrase;

[0042] Four, the target languag...

Embodiment 1

[0049] Human language, also called natural language, exists in the form of words. In order to calculate the similarity of the language itself, it is necessary to represent the human language in the form of vectors. There are many ways to implement the process of representing human language using vectors. This example uses the word vector representation based on deep learning and extends it to phrase representation. In this embodiment, the establishment process of a Chinese "beginning" to Spanish "iniciar" translation rule with English as the pivotal language is taken as an example to specifically illustrate the technical solution of the present invention, which specifically includes the following steps (such as figure 1 shown):

[0050] Step 1: Establish the source language-pivot language translation rule base, and express the pivot language phrases in vector form in the source language-pivot language translation rule base.

[0051] Step 2, in the pivot language-target langu...

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 pivot language translation method and device based on similarity matching, and belongs to the technology field of machine translation. The pivot language translation method and device based on similarity matching solve the problems that in source language to target language translation rule library construction through an existing translation method and device, pivot language phrases of translation rules from a source language to a pivot language and pivot language phrases of translation rules from the pivot language to the source language are required to be identical, and accordingly potential translation rules are lost. The pivot language phrases are represented through vectors and matching association is carried out on the pivot language through the cosine value of a vector angle, a source language to target language translation rule library is built, and natural language translation is carried out through the source language to target language translation rule library. By means of the steps, a pivot language translation device based on similarity matching is manufactured in a modularized mode. The pivot language translation method and device are used for natural language translation.

Description

technical field [0001] The invention belongs to the technical field of machine translation, and relates to a pivot language translation method and device based on similarity matching. Background technique [0002] Statistics-based machine translation technology emerged in the 1990s. It can automatically extract translation rules from bilingual parallel corpora without manual intervention and has wide language applicability. It is currently the most widely used machine translation system. The translation quality of statistical-based machine translation systems largely depends on the quality of bilingual parallel corpora. The higher the quality of the corpus and the higher the amount of data, the higher the quality of the translation obtained by the statistical machine translation system using that corpus. But for most language pairs, there is a problem of not being able to obtain a sufficient amount of high-quality corpus. [0003] Aiming at the problem of sparse corpus, th...

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 朱聪慧朱晓宁赵铁军郑德权杨沐昀曹海龙徐冰
Owner 严格集团股份有限公司
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