Entity word recognition result evaluation method, device and equipment and entity word extraction system

A technology of recognition results and recognition methods, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of inability to recognize the correct and wrong results of entity word recognition, poor entity word recognition effect, etc., to improve accuracy rate and improve the recognition effect

Pending Publication Date: 2019-05-07
XINHUANET CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, there may still be recognition errors in the entity word recognition results identified by existing entity recognition methods. In the prior art, it is impossible to judge the correctness and error of the entity word recognition results, resulting in poor recognition effect of entity words

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 word recognition result evaluation method, device and equipment and entity word extraction system
  • Entity word recognition result evaluation method, device and equipment and entity word extraction system
  • Entity word recognition result evaluation method, device and equipment and entity word extraction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present application, and should not be construed as limiting the present invention.

[0036] Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and / or groups thereof. It will be u...

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 embodiment of the invention provides an entity word recognition result evaluation method, device and equipment and an entity word extraction system. The method comprises: acquiring an entity wordrecognition result of a to-be-recognized document set, wherein the entity word recognition result is an entity word recognition result corresponding to any determined entity word recognition method byconducting entity word recognition on the to-be-recognized document set on the basis of at least one entity word recognition method; Determining a first weight of any to-be-evaluated entity word in the entity word recognition result corresponding to the at least one entity word recognition method in the to-be-recognized document set; And determining a second weight of any entity word to be evaluated based on the first weight of any entity word to be evaluated, the accuracy of the at least one entity word recognition method and the penalty coefficient of the at least one entity word recognition method, the second weight being used for evaluating any entity word to be evaluated. According to the scheme of the embodiment, the correctness of the entity word recognition result is judged through the second weight, and the entity word recognition effect is effectively improved.

Description

technical field [0001] The present application relates to the technical field of language processing. Specifically, the present application relates to a method, device, equipment, and entity word extraction system for evaluating entity word recognition results. Background technique [0002] With the popularity of the Internet and the rise of the mobile Internet, and the advent of the era of media and self-media, network content has increased dramatically. In a large number of event reports, we cannot read all the news reports at one time, and we cannot know the relevant people, places, and related institutions of the main event reports. This requires a system to extract the entity word information of the event and the entity word in real time. Evaluate weights to assist readers to predict the development and changes of events in advance. [0003] Entity recognition is an important research direction of natural language processing. Its purpose is to identify words representi...

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): G06F17/27G06F16/182
CPCY02D10/00
Inventor 韩勇赵立永吴新丽
Owner XINHUANET 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