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

Dependency grammar analysis method and device and auxiliary classifier training method

A technology that depends on syntax and training methods, and is applied in the directions of instruments, calculations, and electrical digital data processing, etc. It can solve the problems of time-consuming and labor-intensive training, and the inability to train high-precision statistical dependency syntax analysis models, so as to achieve accurate analysis results, high-performance transplantation, and improved The effect of accuracy

Inactive Publication Date: 2014-01-15
FUJITSU LTD
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the other hand, the labeling of the dependency parsing treebank suitable for a certain field needs to be done by experts in linguistics, which is a time-consuming and laborious task
Therefore, in many applications, the target domain has little or no labeled data, and it is impossible to train a high-precision statistical dependency parsing model for a specific domain.

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
  • Dependency grammar analysis method and device and auxiliary classifier training method
  • Dependency grammar analysis method and device and auxiliary classifier training method
  • Dependency grammar analysis method and device and auxiliary classifier training method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0025] According to the first embodiment of the present invention, a dependency syntax analysis-assisted classifier training method is proposed. figure 1 A schematic flowchart of the method is shown.

[0026] Such as figure 1 As mentioned above, in step S110, a general dependency syntax analyzer is used to perform dependency syntax analysis on each sentence in the tagged corpus of the target domain, and N analysis results are obtained for each sentence. Here, Chinese is taken as an example for description. It should be noted that the embodiments of the present invention only use Chinese as an illustrative example, but the present invention is not limited thereto. Those skilled in the art can also apply it to natural languages ​​such as English, Japanese or Korean.

[0027] The following example illustrates. When each tagged sentence is analyzed using the general dependency parser, a list of N analysis results is generated for each sentence. N is an indeterminate value. ...

no. 2 approach

[0042] According to one aspect of the present invention, a dependency syntax analysis method is provided. In this method, a general-purpose dependency parser is also used for dependency parsing, but the analysis object is the unlabeled corpus of the target domain. In addition, the method also uses the auxiliary classifier obtained in the first embodiment to classify the analysis results. Figure 4 A schematic flowchart of the method is shown.

[0043] Such as Figure 4 As shown, in step S410, a general dependency syntax analyzer is used to perform dependency syntax analysis on sentences in the target domain, and a predetermined number of analysis results are generated. It should be noted that the sentences that are analyzed in this step are unlabeled corpus in the target field.

[0044] Here, the "predetermined quantity" can be determined according to the requirements for the accuracy of the analysis results. That is to say, if you want to obtain analysis results with high...

no. 3 approach

[0049] According to one aspect of the present invention, a device for analyzing dependency syntax is provided. Figure 5 A schematic structural diagram of a dependency syntax analysis device 500 according to an embodiment of the present invention is shown. Figure 6 A working principle diagram of the dependency syntax analysis device according to the present invention is shown. Such as Figure 5 As shown, the dependency syntax analysis device 500 may include a general dependency syntax analyzer 510 , a feature extraction unit 520 and an auxiliary classifier 530 . Refer below Figure 6 The working process of the dependency syntax minute device 500 is described.

[0050] Such as Figure 6 As mentioned above, the dependency syntax analysis device 500 receives unmarked target domain data. The received target domain data is input to the generic dependency parser 510 . Dependency analysis is performed on the target domain data in the general dependency syntax analyzer 510 to g...

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 dependency grammar analysis method and device and an auxiliary classifier training method. The dependency grammar analysis method includes the steps of preliminary analysis: using a universal dependency grammar analyzer to carry out dependency grammar analysis on sentences of a target field to generate analysis results in a predetermined number, characteristic extraction: extracting the high-order characteristics of at least parts of edges from a dependency relationship tree serving as the analysis results, and classification: using an auxiliary classifier to classify the analysis results in the predetermined number based on the high-order characteristics, and selecting final dependency grammar analysis results from the analysis results in the predetermined number according to the classification results.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular, the invention relates to a natural language dependency syntax analysis auxiliary classifier training method, a dependency syntax analysis method and a device. Background technique [0002] Dependency analysis of natural language refers to revealing its syntactic structure by analyzing the dependency relationship between components within a language unit. In dependency syntactic analysis, the central component in a sentence is regarded as the main component that dominates other components, but it itself is not dominated by any other components, and all the dominated components are subordinate to the dominator in a certain dependence relationship. The result of dependency analysis usually takes the form of a syntax tree, which is composed of edges and nodes, and the syntax trees of different shapes composed of edges and nodes represent different syntax analysis results for ...

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): G06F17/27G06F17/30
Inventor 郑仲光孟遥于浩
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