Sequence labeling method and device and training method of sequence labeling model

A sequence labeling and model technology, applied in the direction of neural learning methods, biological neural network models, special data processing applications, etc., can solve problems such as the inability to improve model labeling performance

Active Publication Date: 2019-09-06
SUZHOU UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a sequence labeling method, device, training method, equipment and computer-readable storage medium of a sequence labeling model

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
  • Sequence labeling method and device and training method of sequence labeling model
  • Sequence labeling method and device and training method of sequence labeling model
  • Sequence labeling method and device and training method of sequence labeling model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0052] The following introduces Embodiment 1 of a sequence tagging device provided by the present application, and Embodiment 1 includes a sequence tagging model. It should be noted that, in this embodiment, a deep neural network is used as the above-mentioned sequence labeling model to avoid the shortcomings of traditional feature engineering-based models, such as cumbersome feature extraction process and difficulty in ensuring the rationality of feature templates. As a specific implementation, this embodiment selects BiLSTM (Bidirectional Long Short-Term Memory) as the basic model.

[0053] see figure 1 , the above sequence labeling model specifically includes:

[0054] Input layer 101: for obtaining text to be marked;

[0055] Presentation layer 102: for determining the vector representation of each word of the text to be marked, and sending the vector representation to the first scoring layer 103 and multiple second scoring layers 104 respectively;

[0056] In this embo...

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 sequence labeling method and device, a training method and equipment of a sequence labeling model and a computer readable storage medium. In the scheme, a score layer of a sequence labeling model comprises second score layers which are in one-to-one correspondence with labeling specifications. The invention comprises a first score layer corresponding to all the labeling specifications. Due to the unique design of the score layer in the model, heterogeneous data of multiple annotation specifications can be used as a training set of the model, the scale of training corpora is expanded, and the model can learn the generality of corpora of different annotation specifications, so that the annotation performance of the model under a single annotation specification is improved. Besides, the output result of the model is a binding label sequence, equivalently, the label sequence under various labeling specifications is directly obtained, and conversion of the text between different labeling specifications is facilitated.

Description

technical field [0001] The present application relates to the field of natural language processing, and in particular to a sequence tagging method and device, a sequence tagging model training method, equipment, and a computer-readable storage medium. Background technique [0002] In natural language processing tasks, it is often necessary to use labeled data as training samples for natural language processing models, where the scale of labeled data significantly affects the performance of the model. Since the construction cost of manually labeled data is very expensive, some scholars have proposed a solution to expand the scale of data by using heterogeneous data resources. However, since heterogeneous data follow different annotation specifications, it is impossible to directly mix heterogeneous data. Therefore, how to effectively use heterogeneous data to improve model performance has become a research problem. [0003] At present, a solution to improve model performanc...

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): G06F17/27G06N3/04G06N3/08
CPCG06N3/08G06F40/289G06N3/045
Inventor 李正华黄德朋张民
Owner SUZHOU 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