Named entity identification method and device, equipment and medium

A named entity recognition and overall technology, applied in the computer field, can solve problems such as poor recognition effect

Active Publication Date: 2020-07-07
北京香侬慧语科技有限责任公司
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in a sentence, the characters occupied by entities only account for a small number of all characters, most of the characters need to be marked as "negative samples" by the model, and there are many easy samples in the negative samples, so the learning of the model will be Most of them are easily controlled by negative samples, resulting in poor entity recognition

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
  • Named entity identification method and device, equipment and medium
  • Named entity identification method and device, equipment and medium
  • Named entity identification method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Embodiment 1 of the present invention provides a named entity recognition method, figure 1 A flowchart showing an embodiment of the named entity recognition method of the present invention, including:

[0049] Step S101: input the target sentence into the current named entity recognition model, and obtain the tag type and corresponding probability of each character in the target sentence;

[0050] In this embodiment, the sentence to be recognized by named entity is input into the current named entity recognition model, and each character in the sentence is marked separately to obtain the type of label and the corresponding probability. The named entity recognition model used such as BERT model, LSTM -CRF model, etc. For example, the target sentence is "I love Beijing", input the sentence into the current named entity recognition model, and mark each character in the sentence as "B (Begining)" and "M (Middle)" , one of the "E(End)" or "O(Outside)" labels, to get the lab...

Embodiment 2

[0086] The named entity recognition device described below and the named entity recognition method described above may refer to each other correspondingly.

[0087] The embodiment of the present invention also provides a named entity recognition device, Image 6 It shows a schematic structural diagram of an embodiment of the named entity recognition device of the present invention, including:

[0088] Annotation module 101, is used for inputting target sentence into current named entity recognition model, obtains the labeling type and corresponding probability of each character in described target sentence;

[0089] The loss value acquisition module 102 is configured to calculate the corresponding loss value of the label type of each character according to the corresponding probability of the label type of each character according to the target loss function, and according to the current loss value Calculating an overall loss value, the target loss function increases the atte...

Embodiment 3

[0101] Based on the above solution, the present invention also provides a named entity recognition device, including the above-mentioned named entity recognition device, and details of the named entity recognition device will not be repeated here.

[0102] In addition, the embodiment of the present application also provides a named entity recognition device, such as Figure 7 As shown, the equipment includes:

[0103] memory 11 for storing computer programs;

[0104] The processor 12 is used to implement the following steps when executing the computer program: input the target sentence into the current named entity recognition model to obtain the label type and corresponding probability of each character; according to the corresponding probability of the label type of each character according to The target loss function calculates the corresponding loss value, calculates the overall loss value according to the current loss value, and the target loss function increases the att...

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 named entity recognition method, a named entity recognition device, equipment and a medium. The named entity recognition method comprises the steps of: inputting a target sentence into a current named entity recognition model, and acquiring an annotation type and a corresponding probability of each character; calculating a corresponding loss value based on a target loss function according to the corresponding probability of the annotation type of each character, calculating a total loss value according to the current loss values, and improving the attention of the named entity recognition model to the characters with high annotation type uncertainty by using the target loss function; judging whether the current named entity recognition model meets a convergence condition or not; if not, selecting the model with the optimal current effect as a target model to perform entity identification on the target sentence; and if so, updating the named entity recognitionmodel according to the total loss value to obtain an updated named entity recognition model, circulating the previous steps until the judging that the named entity recognition model meets a convergence condition, thereby being capable of increasing the accuracy rate of named entity recognition.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a named entity recognition method, device, equipment and medium. Background technique [0002] Named entity recognition refers to the identification of entities with specific meaning in text, mainly including names of people, places, institutions, proper nouns, etc. In order to obtain more accurate results on the task of named body recognition, that is, to identify possible named entities (such as person names, place names, organization names, etc.) in a sentence, the traditional method maps each word in the vocabulary to a Word vectors, and encode the word vectors in the entire sentence through some encoders, and finally predict the label to which each word belongs. [0003] However, in a sentence, the characters occupied by entities only account for a small number of all characters, most of the characters need to be marked as "negative samples" by the model, and ther...

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): G06F40/295G06K9/62
CPCG06F18/214
Inventor 韩庆宏李纪为
Owner 北京香侬慧语科技有限责任公司
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