Text classification method and device based on multi-task learning and electronic equipment
A multi-task learning and text classification technology, which is applied in the text classification method based on multi-task learning, electronic equipment, storage media, and device fields, can solve the problem that negatively related tasks cannot be grouped into the same cluster, and improve the generalization ability , the effect of enhancing the effect
Pending Publication Date: 2022-05-13
海南中信达信息技术有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although this method can save the determination of the number of task clusters, due to the use of l 2 Norm distance to measure the similarity between task parameters, so negatively related tasks cannot be grouped into the same cluster
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
Embodiment Construction
[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0044]On the one hand, the embodiment of the present invention provides a text classification method based on multi-task learning, such as figure 1 shown, including:
[0045] Step 101: input feature vector set of text data and its corresponding label value;
[0046] In this step, the feature vector set D of the data i =(x ij ,y ij ),j=1,2,...,N i} can be represented by N i The eigenvectors of samples, where N i Indicates the number of samples i...
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 embodiment of the invention discloses a text classification method and device based on multi-task learning, electronic equipment and a storage medium, and belongs to the technical field of text processing, and the text classification method based on multi-task learning comprises the following steps: inputting a feature vector set of text data and a tag value corresponding to the feature vector set; segmenting all texts into a training data set and a test data set according to a certain proportion; determining a value of a task number m, and averagely distributing samples of the training data set to m tasks; solving the model to obtain a regression matrix W; and utilizing the regression matrix W to carry out regression on samples of the test data set, and estimating a label estimation value of the test text so as to finish classification of the test text. According to the method, the generalization ability of all the tasks is improved by transmitting knowledge among the tasks, so that the text classification effect is improved.
Description
technical field [0001] The invention relates to the technical field of text processing, in particular to a text classification method, device, electronic equipment and storage medium based on multi-task learning. Background technique [0002] Text classification can be widely used in many scenarios such as spam detection, sentiment classification and article classification topics. However, the current text classification methods often split the connection between samples and ignore the shared information between data, resulting in poor classification results. [0003] In multi-task learning, however, multiple tasks are jointly learned so as to share information among related tasks. The purpose of multi-task learning is precisely to improve the generalization ability of all tasks by transferring knowledge among multiple tasks. Therefore, text classification based on multi-task learning can achieve better results. [0004] The main challenge of multi-task learning is how to...
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 IPC IPC(8): G06F16/35G06F16/33G06K9/62G06N20/00
CPCG06F16/35G06F16/3344G06N20/00G06F18/214
Inventor 张晓飞
Owner 海南中信达信息技术有限公司