Multi-label text classification method based on BiGRU and attention mechanism

A text classification and attention technology, applied in the direction of text database clustering/classification, text database query, unstructured text data retrieval, etc., can solve the problem of limited, unable to effectively identify words or popular words, etc., and achieve high training time. , the effect of shortened training time, wide applicability

Pending Publication Date: 2020-08-11
SHANGHAI MUNICIPAL ELECTRIC POWER CO
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The arrival of the Internet era has promoted the birth of many new words, which has a great impact on the sentiment classification model based on the emotional polarity dictionary. The existing emotional polarity dictionary is limited, and the model cannot effectively identify newly generated words or popular words.

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
  • Multi-label text classification method based on BiGRU and attention mechanism
  • Multi-label text classification method based on BiGRU and attention mechanism
  • Multi-label text classification method based on BiGRU and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below in conjunction with accompanying drawing, by describing a preferred specific embodiment in detail, the present invention is further elaborated.

[0031] Text classification is an important part of natural language processing. In grid-related network text emotion recognition, for the problem that the text has no fixed grammar and writing format, and the emotional information is scattered in each position of the text, the present invention provides a two-way based A multi-label text classification method of gated recurrent neural network (BiGRU) and attention mechanism, the method includes the following steps:

[0032] S1. Obtain several pieces of network text.

[0033] S2. Preprocessing several web texts.

[0034] In this embodiment, the first m characters of each web text are extracted as its input neurons, and web texts with less than m characters are automatically filled with spaces.

[0035] S3. Use the pre-trained word vector to extract the deep information ...

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 provides a multi-label text classification method based on BiGRU and an attention mechanism. The method comprises the following steps: S1, acquiring a plurality of web texts; s2, preprocessing the plurality of web texts; s3, extracting deep information features of the web text by using the pre-trained word vector; s4, adding corresponding weights to the deep information features according to an attention mechanism; s5, performing probability classification of different types of labels on the data obtained in the step S4 by using BiGRU; and S6, outputting the probability of each web text on different types of labels. The method has the advantages that the pre-training word vector is adopted to further shorten the training time, the attention mechanism is adopted to enable theneural network to focus on important information for improving the classification effect, and compared with the prior art, the BiGRU and the attention mechanism are fused to enable the method to obtain the same high accuracy by using less training time.

Description

technical field [0001] The present invention relates to the field of network text classification, in particular to a multi-label text classification method based on BiGRU and attention mechanism. Background technique [0002] Emotion recognition is one of the important topics in natural language processing. Today, when the Internet is highly developed, people post online through Weibo, news websites, forums, etc. The length of these speeches is variable, the vocabulary is not limited, and there are no strict grammatical rules, which have a strong subjective tendency. Among them, negative speech is an important topic that needs urgent attention. If the emotion of speech cannot be correctly identified, it will be impossible to prevent the occurrence of cyber violence in time and prevent behaviors that endanger the reputation of individuals and even enterprises. In this context, grid-related network text emotion recognition has high research significance. [0003] Text emotio...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/33G06F16/35G06F40/284G06N3/04
CPCG06F16/3346G06F16/35G06F40/284G06N3/045
Inventor 施凌鹏卢士达顾中坚李天宇张黎首刘逸逸李姝黄静韬吴金龙沈邵骏
Owner SHANGHAI MUNICIPAL ELECTRIC POWER CO
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