Text language association relationship labeling method and device

A related relationship and text technology, applied in the information field, can solve problems such as the inability to achieve global optimization, and achieve the effect of improving accuracy and recall

Active Publication Date: 2020-10-02
PEKING UNIV +3
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This two-stage training method cannot achieve global optimization

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
  • Text language association relationship labeling method and device
  • Text language association relationship labeling method and device
  • Text language association relationship labeling method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below through specific embodiments and accompanying drawings.

[0037] figure 1 It is a schematic diagram of a text-language association labeling method in an embodiment of the present invention, wherein (a) is a composite labeling system of this labeling method applied to a joint learning framework for named entity recognition and entity standardization, and (b) is an application of this labeling method A composite annotation system based on the joint learning framework of named entity recognition and relationship extraction. The text-language association-relation labeling method of the present invention is applicable to the joint learning of multiple text-language-associated subtasks. Here, only two examples are joint learning of named entity recognition and entity standardization and joint learning of name...

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 text language association relationship labeling method and device. The close relevance of each information extraction subtask of the text language is utilized; a composite labeling method independent of a specific model is designed; a plurality of text language information extraction tasks can be naturally fused; joint learning and integrated training of multiple text language association tasks are achieved, for example, joint learning supporting named entity recognition and named entity standardization, joint learning supporting named entity recognition and entity relationship extraction, joint learning supporting named entity recognition and entity disambiguation and the like. According to the text language association relationship composite labeling method provided by the invention, the close association among the sub-tasks of text language information extraction is fully utilized, and complete joint learning is realized, so that information sharing among the associated tasks can be mutually promoted, and the accuracy and recall rate of text language information extraction are improved on the whole.

Description

technical field [0001] The invention belongs to the field of information technology, and relates to information extraction of text language assisted by computer intelligence technology. Specifically, it involves the use of the close relevance of the sub-tasks of text language information extraction, designing a composite labeling method to naturally integrate multiple text language information extraction tasks, and realizing joint learning and integrated training of multiple text language related tasks. It enables information sharing and mutual promotion between related tasks, and improves the accuracy and recall rate of text language information extraction. Background technique [0002] As the main form of expression of natural language, text language is an important carrier of information. In today's era of information explosion, how to extract useful structured information from massive unstructured texts is the key to data intelligence. Information extraction in text la...

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): G06F40/117G06F40/295
Inventor 韩英刘迪王腾蛟邱镇陈薇孟洪民
Owner PEKING UNIV
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap