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

Phrase division model establishing method, statistical machine translation method and decoder

A technology of phrases and models, applied in the fields of instruments, computing, special data processing applications, etc., can solve problems such as high complexity and limited syntactic analysis accuracy, and achieve the effect of improving the quality of machine translation

Active Publication Date: 2011-09-21
FUJITSU LTD
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, what these methods have in common is that they all use syntactic information to limit rule matching, so they are limited by the accuracy of syntactic analysis and have high complexity.

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
  • Phrase division model establishing method, statistical machine translation method and decoder
  • Phrase division model establishing method, statistical machine translation method and decoder
  • Phrase division model establishing method, statistical machine translation method and decoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Embodiments of the present invention will be described below with reference to the drawings. Elements and features described in one drawing or one embodiment of the present invention may be combined with elements and features shown in one or more other drawings or embodiments. It should be noted that representation and description of components and processes that are not related to the present invention and known to those of ordinary skill in the art are omitted from the drawings and descriptions for the purpose of clarity.

[0054] An object of the present invention is to determine phrase boundaries by dividing sentences into phrases, thereby constraining rule matching and improving translation quality.

[0055] For this reason, firstly, the present invention proposes a method for establishing a phrase division model. The phrase segmentation model established by the method can be incorporated into the decoder during the translation process to improve the translation q...

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 phrase division model establishing method, a statistical machine translation method and a decoder. The phrase model establishing method comprises the following steps of: acquiring a training sample from a bilingual corpus; inputting the acquired training sample to a parameter training tool of a maximum entropy model, and performing parameter training to acquire a weight parameter of the maximum entropy model; and substituting the weight parameter into the maximum entropy model to generate a phrase division model.

Description

technical field [0001] The invention relates to the field of statistical machine translation, in particular to a method for establishing a phrase division model, a statistical machine translation method and a decoder. Background technique [0002] The statistical machine translation method based on hierarchical phrases is a mainstream method in the field of statistical machine translation in recent years. In the hierarchical phrase model, phrases are allowed to contain subphrases, and the variable X is used to replace subphrases, so that the model has generalization ability. That is, translation knowledge learned from one phrase can be used to translate other phrases with the same pattern. [0003] For example, for the following phrase pairs: [0004] Phrase pair 1: visit China in April "四月, April" and "China, China" can be regarded as two sub-phrases. respectively with X 1 and x 2 Instead of these two subphrases, a translation rule can be obtained: [0005] Rule 1: X-...

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): G06F17/28G06F17/27
Inventor 何中军孟遥于浩
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