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

Instance-based dynamic generalization coreference resolution method

A coreference resolution and generalization technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as misclassification, and achieve strong adaptability and effective effects

Inactive Publication Date: 2010-12-01
HARBIN INST OF TECH
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, the final learned model can only cover most cases, and there is a possibility of misclassification for some low-frequency instances.

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
  • Instance-based dynamic generalization coreference resolution method
  • Instance-based dynamic generalization coreference resolution method
  • Instance-based dynamic generalization coreference resolution method

Examples

Experimental program
Comparison scheme
Effect test

example

[0129] Step 3-3 Filter the instance set:

[0130] delete g* from G, and add g* to G';

[0131] Utilize the best generalization point g*, filter all instances with g* in the training instance subset currently to be screened, and set E'={all instances with generalization point g* in the original E'}.

[0132] It should be emphasized that the screening of the subset of training examples involves the matching method of generalization points. During the implementation process, the exact matching method is adopted for the matching of enumerated and definite infinite generalization points; while for infinitely variable generalization points, the nodes in the graph structure are gradually deleted to relax the constraints until the pruned substructure is at least Appears as a subgraph in a training instance, and the training instance is filtered with this substructure.

[0133] Step 3-4 Iteration termination condition determination:

[0134] If the instances in E' all belong to the ...

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 an instance-based dynamic generalization coreference resolution method, and relates to the field of text information extraction. The dynamic generalization coreference resolution method comprises a training instance library establishment stage and an in-discourse entity resolution stage, and the coreference resolution is finished by instance establishment, instance library establishment, index creation, dynamic generalization, instance retrieval and coreference chain combination. The method eliminates the long tail effect in a coreference statistical model, fully achieves the effect of a low-frequency training sample, makes full use of the precious training sample, and makes the dynamic generalization mechanism of the instances self-adaptively convert the classification of test instances into the selection and utilization of the best generalization point in a training instance library and finally find the optimally matched training instance.

Description

technical field [0001] The invention relates to the field of text information extraction, in particular to an instance-based dynamic generalization coreference resolution method. Background technique [0002] In recent years, with the explosive growth of information on the Internet, new information appearing every day greatly exceeds the processing ability of human beings. In natural language processing, information retrieval and many other fields, the same thing in the real world often has different names and descriptions. Correctly corresponding them to specific things is very necessary for subsequent processing and in-depth understanding of data. In natural language processing, the resolution of nouns, pronouns, and common noun phrases pointing to the same entity can make the description of the subsequent entity relationship more perfect. foundation for information retrieval. The so-called coreference resolution is to divide the equivalence classes of all expressions a...

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): G06F17/27G06F17/30
Inventor 秦兵刘挺郎君黎耀炳张牧宇
Owner HARBIN INST OF TECH
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