Entity labeling method in named entity identification and intelligent equipment

A named entity recognition and entity technology, which is applied in the fields of instruments, electrical digital data processing, and computing, and can solve problems such as the inability to truly guarantee the accuracy, frequency, and poor generalization of entity labeling.

Pending Publication Date: 2020-11-17
HISENSE VISUAL TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the methods based on dictionaries and rules mainly rely on dictionaries and manual rules. The construction of manual rules consumes a lot of manpower, and the generalization is poor. The problem of unregistered words cannot be dealt with based on dictionaries; and rules, but at the same time there is also the problem of over-reliance on feature construction; mainstream deep learning-based methods optimize the problem of machine learning over-reliance on featu...

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
  • Entity labeling method in named entity identification and intelligent equipment
  • Entity labeling method in named entity identification and intelligent equipment
  • Entity labeling method in named entity identification and intelligent equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the purpose, implementation and advantages of the application clearer, the following will clearly and completely describe the exemplary embodiments of the application in conjunction with the accompanying drawings in the exemplary embodiments of the application. Obviously, the described exemplary embodiments It is only a part of the embodiments of the present application, but not all the embodiments.

[0025] Based on the exemplary embodiments described in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts fall within the protection scope of the appended claims of this application. In addition, although the disclosures in this application are introduced as exemplary one or several examples, it should be understood that each aspect of these disclosures can also independently constitute a complete implementation.

[0026] It should be noted that the brief description of the terms in this...

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 entity labeling method in named entity recognition and intelligent equipment, and the method comprises the steps: inputting a target entity into a joint model after the target entity in a text is recognized; wherein the joint model comprises a semantic index model for similarity query and a word meaning classification model; and according to a constraint function, constraining the word meaning category output by the joint model and the entity link of the knowledge graph, and finally outputting the high-frequency word meaning category of the target entity. The problemthat the entity labeling result is uncontrollable can be solved, the deviation of the entity labeling result is reduced, and then the named entity recognition accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an entity labeling method and an intelligent device in named entity recognition. Background technique [0002] Named Entities Recognition (NER) is a basic link in Natural Language Processing (NLP). An important basic tool for many NLP tasks such as syntax analysis and machine translation. At present, NER is mainly evaluated in two aspects: one is the accuracy of entity boundary recognition, and the other is the accuracy of entity labeling. Entity labeling mainly labels the word sense category of entities. Due to factors such as the infinite number of named entities, the flexibility of word formation, and the ambiguity of semantics, entity labeling has become one of the technical problems in this field. [0003] At present, named entity recognition mainly includes methods based on dictionaries and rules, methods based on traditional machine learning, and meth...

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): G06F40/295
CPCG06F40/295
Inventor 张桐桐殷腾龙
Owner HISENSE VISUAL TECH CO LTD
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