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

Machine translation method and system

A machine translation and syntax analysis technology, applied in the field of natural language processing research, can solve the problems of large number of redundant rules and poor machine translation performance, and achieve the effect of improving performance

Active Publication Date: 2018-02-13
BEIJING JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] In order to solve the problem that the number of redundant rules in the extracted hierarchical phrase translation rules in the prior art is very large, resulting in very poor machine translation performance, the embodiment of the present invention provides a machine translation method and system

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
  • Machine translation method and system
  • Machine translation method and system
  • Machine translation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0092] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0093] figure 1 It is a method flow chart of the machine translation method provided in an embodiment of the present invention. The machine translation system can be implemented as part or all of the computer through software, hardware or a combination of the two. The machine translation method includes a translation step comprising:

[0094] Step 101: Obtain an input source language test sentence;

[0095] Step 102: Perform lexical analysis on the source language test sentence to obtain the lexical analysis result of the source language test sentence;

[0096] Step 103: Perform syntactic structure analysis on the lexical analysis result of the source language test sentence to obtain the syntactic analysis result of the source langua...

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 discloses a machine translation method and system, belonging to the field of natural language processing research. The method includes: training process and translation process, by extracting the predicate argument structure of the source language sentence, combining the word string of the lexical analysis result of the target language, forming a tree-to-string bilingual alignment corpus, and then using the predicate argument structure information to guide the tree The extraction and decoding process of string-to-string machine translation rules, thus directly modeling the predicate argument structure into tree-to-string machine translation. The present invention solves the problem that the number of redundant rules in the statistical translation rules extracted in the prior art is very large by modeling the predicate argument structure into the tree-to-string machine translation, thereby reducing the number of redundant rules and improving semantics Structural and semantic correlations, improved long-distance sequencing performance, and improved translation quality.

Description

technical field [0001] The invention relates to the field of natural language processing research, in particular to a machine translation method and system. Background technique [0002] At present, the mainstream methods of machine translation can be roughly divided into rule-based and corpus-based methods, and corpus-based methods can be subdivided into instance-based methods and statistics-based methods. The machine translation method based on statistics can use the bilingual parallel corpus as the learning data, automatically obtain the translation rules through training, and at the same time, combine the language model to translate the test sentences. With the continuous improvement of statistical machine translation models, word-based, phrase-based and syntactic structure-based statistical models have appeared successively, and the translation quality has been continuously improved. [0003] However, traditional statistical machine translation models make more use of ...

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): G06F17/28G06F17/27
Inventor 徐金安吴培昊
Owner BEIJING JIAOTONG UNIV
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