Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Language entity relationship analysis method and a machine translation device and method

An entity relationship and analysis method technology, which is applied in the fields of natural language processing and machine translation systems, language entity relationship analysis, and machine translation devices, and can solve problems such as the inability to improve the effect of language processing and the explosion of combinations.

Active Publication Date: 2016-08-17
刘建勇 +2
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Since the rule system, statistical system, or early semantic system did not focus on solving the core problem of language, that is, the "combination explosion" problem, on the contrary, it has been deeply troubled by the "combination explosion" for a long time, so that the language processing effect has been unable to improve.

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 entity relationship analysis method and a machine translation device and method
  • Language entity relationship analysis method and a machine translation device and method
  • Language entity relationship analysis method and a machine translation device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0143] The present invention will be described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0144] Such as image 3 As shown, the implementation flow chart of the overall technical solution of the language entity relationship analysis method provided by the present invention, the method includes the following steps:

[0145] (1): Segment the input sentence into chapters, paragraphs, and large sentences, and perform step (2); then, within the scope of paragraphs and large sentences, perform knowledge calculations such as default reference;

[0146] (2): The large sentence is divided into small sentences, and the step (3) is carried out;

[0147] (3): The embedded processing in the clause calls step (2); after the embedded processing is completed, proceed to step (4);

[0148] Embedded instructions, such as the statement: "I know this method (use solution A to solve the problem); "string" (use A solution to solve the problem)" i...

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 language entity relationship analysis method, which relates to the field of natural language processing. The method carries out all-solution and integrated calculation on input language strings, and selects an optimal semantic tree. The present invention also provides a machine translation device and method based on the language entity relationship analysis method. The translation device includes a semantic knowledge base module, a language entity relationship analyzer, and a target language generator. The present invention provides a brand-new language processing model. In the program, grasp all the logic of natural language, make full use of "combination explosion", establish a perfect language logic framework, and basically solve the core problem of language "combination explosion". Can significantly improve accuracy and translation speed. This system does not have a large number of production rules of the rule system, nor does it have the massive alignment corpus and corresponding deep processing resources of the statistical system, which has obvious advantages in engineering. The invention can also provide a reliable basis for various applications of natural language.

Description

technical field [0001] The present invention relates to the field of natural language processing, and more specifically relates to a language entity relationship analysis method and a machine translation device and method for natural language processing and machine translation systems. Background technique [0002] High-quality processing of open data sources such as Internet data and the urgent need to understand different language civilizations have made natural language processing and machine translation at the core of language intelligence research for decades. [0003] At present, the rule system and statistical system are the mainstream technical solutions for natural language processing and machine translation. [0004] There are more than 10,000 to 100,000 rules in the rule system; tens of thousands or hundreds of thousands of template rules. The steps to analyze the execution system are relatively simple. 1-best, 7-best, 30-best and other compromise solutions are ...

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): G06F17/27G06F17/28
Inventor 刘建勇董亦农尹德春
Owner 刘建勇
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products