Text classification model training method and device and text classification method and device
A technology of text classification and training method, applied in text database clustering/classification, neural learning method, biological neural network model, etc., which can solve the problems of indeterminable differences and low model accuracy
Active Publication Date: 2021-02-23
BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD
View PDF6 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, in the above method, the label vector is randomly initialized and corresponds to the entire label, and has nothing to do with the word unit in the label, that is, it has nothing to do with the semantics of the label. The difference between sample text vectors makes the accuracy of the trained model lower, so a simpler and more convenient method is needed to train the text classification model to obtain a higher accuracy text classification 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 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
[0050] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the specification. However, this specification can be implemented in many other ways different from those described here, and those skilled in the art can make similar extensions without violating the connotation of this specification, so this specification is not limited by the specific implementations disclosed below.
[0051] Terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only, and are not intended to limit one or more embodiments of this specification. As used in one or more embodiments of this specification and the appended claims, the singular forms "a", "said" and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present specification refers t...
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 provides a text classification model training method and device and a text classification method and device. The method comprises the steps that a first vector set and a second vector set are determined according to a first sample text and a label set of a sample text set; the first vector set and the second vector set are input into a word-level attention layer, a third vector set and a fourth vector set are obtained, and the number of third vectors and the number of fourth vectors contained in the third vector set and the number of fourth vectors contained in the fourth vectorset are related to the number of labels in a label set; the third vector set and the fourth vector set are input into a sentence-level attention layer to obtain a first sample text vector set relatedto the label set; the first sample text vector set is input into a full connection layer to obtain a prediction label of the first sample text; and the text classification model is trained based on the prediction label and the first label set corresponding to the first sample text in the label set until a training stop condition is reached. According to the method, the accuracy of the text classification model is improved.
Description
technical field [0001] This specification relates to the technical field of natural language processing, in particular to a text classification model training method and device, a text classification method and device, computing equipment, computer-readable storage media and chips. Background technique [0002] Multi-label text classification is different from multi-label classification. Multi-label classification is to assign one of multiple labels to a text to be classified, while multi-label text classification is to assign multiple labels to each text to be classified. Therefore, multi-label Text classification is a complex and challenging task in natural language processing. [0003] In the prior art, when solving the problem of multi-label text classification, the model to be trained can be trained through sample text and sample label groups to obtain a text classification model for realizing multi-label text classification. Specifically, the sample text and the sampl...
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 Applications(China)
IPC IPC(8): G06F16/35G06N3/04G06N3/08
CPCG06F16/353G06F16/355G06N3/08G06N3/044G06N3/045
Inventor 王得贤李长亮汪美玲
Owner BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD