Text classification model training method, device and readable storage medium
A technology for text classification and training methods, which is applied in the direction of text database clustering/classification, unstructured text data retrieval, etc., to achieve the effect of improving the classification effect
Active Publication Date: 2021-07-16
SUN YAT SEN UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The main purpose of the present invention is to provide a text classification model training method, device and computer-readable storage medium, aiming to solve the problem of improving the classification effect of text classifiers
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
no. 1 example
[0085] refer to figure 2 , the first embodiment of the training method of the text classification model of the present invention, the training method of the text classification model includes:
[0086] Step S10, obtaining the first word vector sequence corresponding to the sample group identified as a positive sample;
[0087] Step S20, obtaining the second word vector sequence corresponding to the sample group of the identified category;
[0088] In this embodiment, the text classification model is trained according to the method proposed by the present invention, that is, the classification parameters of the text classification model are optimized according to the training data.
[0089] The specific application scenario of the text classification model proposed in this embodiment can be used to screen public opinion information from the Food and Drug Administration. Due to the continuous improvement of people's quality of life, the requirements for food and medicine have...
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
Login to View More Abstract
The invention discloses a text classification model training method, which comprises the following steps: extracting the first feature of the positive sample and the second feature of the sample data of the identified category through the feature extraction neural network, and calculating the mean value based on the first feature The square distance is used as a compactness loss, the cross-entropy is calculated based on the second feature as a descriptive loss, and the error loss obtained based on the compactness loss and the descriptive loss is used to train the feature extraction neural network using a backpropagation optimization algorithm. parameters of the network. The invention also discloses a text classification model training device and a computer-readable storage medium. Since the present invention can extract the sample data of the positive sample and the deep features of the sample of the recognized category, calculate the compactness error loss and the descriptive error loss, and adopt backpropagation to the feature extraction neural network through the weighted error loss of the two error losses The algorithm is optimized, thus improving the classification performance of the text classifier.
Description
technical field [0001] The present invention relates to the technical field of text classification, in particular to a text classification model training method, device and computer-readable storage medium. Background technique [0002] With the rapid development of network technology, the requirements for effectively organizing and managing electronic text information and obtaining relevant information quickly, accurately and comprehensively are getting higher and higher. As an important research direction of information processing, text classification is a common method to solve text information discovery. [0003] Text classification is one of the most basic research topics in the field of natural language processing. With the development of deep learning, the supervised learning method makes the classification task of known text categories easier, more efficient and more accurate. In this process, there is sufficient training data to drive the end-to-end learning proces...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35
Inventor 任江涛梁华淇
Owner SUN YAT SEN UNIV