A multi-label text classification method and model
A text classification and label classification technology, applied in text database clustering/classification, neural learning methods, text database query, etc. It can solve the problems of pre-training language model embedding length limitation, single classification task, label long tail phenomenon, etc. Achieve the effect of rich label feature representation
Active Publication Date: 2022-07-08
长沙市智为信息技术有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] Therefore, the technical problem to be solved by the present invention is to overcome the ignorance of the interaction between tags and texts, tags and tags in the prior art, the limitation of the embedding length of the pre-trained language model when embedding, the single classification task, and the long tail of tags. phenomenon, thus providing a multi-label text classification method based on label pre-adaptation and multi-task learning, specifically a multi-label text classification method
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
[0062] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0063] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. The indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must hav...
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 multi-label text classification method and model. The classification method includes a label pre-adaptation task. According to input data of multi-label text classification, a pre-adapted embedded feature representation is obtained, and then similarity matching is performed; The input data of multi-label text classification, and the weight loading of the pre-trained language model in the label pre-adaptation task to obtain the shared feature representation; the parallel classification task uses the shared feature representation as the input of the parallel task, and the parallel task includes chapter-label classification task, keyword-label classification task and label-label correlation judgment task; the classification model includes label pre-adaptation module, shared feature acquisition module, keyword extraction module, label sampling module, chapter-label classification module, keyword-label classification module, and tag-tag correlation judgment module. The invention increases parallel tasks and improves the performance of the model.
Description
technical field [0001] The invention relates to the technical field of label-based text classification, in particular to a multi-label text classification method and model. Background technique [0002] As one of the most important information carriers today, text can enter the Internet through various social platforms, news media and other means. The formats, topics, and contents of these text information are numerous and varied in length. How to reasonably apply and process these text information has become a very urgent requirement. Text classification is a very important task in NLP, and it has a wide range of application scenarios, such as analyzing and classifying cases in smart justice to assist judges in judging cases. [0003] Multi-label text classification is a difficult task in text classification, and it is currently widely used in information retrieval, sentiment analysis, label recommendation, intent recognition and other fields. Different from traditional s...
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): G06F16/33G06F16/35G06F40/289G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/3344G06F16/35G06F40/289G06F40/30G06N3/08G06N3/047G06N3/045G06F18/241G06F18/2415
Inventor 李芳芳苏朴真黄惟康占英王青
Owner 长沙市智为信息技术有限公司