A Text Classification Method Hybrid Long Short-Term Memory Network and Convolutional Neural Network
A convolutional neural network, long-term and short-term memory technology, applied in neural learning methods, biological neural network models, text database clustering/classification, etc., can solve the problem of high cost, time-consuming and laborious, and does not consider the context information of language units in sentences and other issues to achieve the effect of improving accuracy, good effect and good versatility
Inactive Publication Date: 2019-10-18
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Before the 1990s, automatic text classification was mainly based on knowledge engineering, that is, manual classification by professionals, and its disadvantages were high cost, time-consuming and laborious
Existing research and applications have proved that recurrent neural networks are suitable for learning long-term dependencies between language units in sentences, and convolutional neural networks are suitable for learning local features of sentences, but current research has not fully combined recurrent neural networks and Convolutional neural networks have their own advantages, and they do not take into account the context information of language units in sentences
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
[0025] The present embodiment provides a text classification method of mixing long-short-term memory network and convolutional neural network, and the method comprises the following steps:
[0026] Step 1. Preprocessing the sentences in the text, including punctuation filtering, abbreviation completion, deleting spaces, sentence segmentation and illegal character filtering, combined with the length distribution and mean square error of sentences in the training corpus, after determining the sentence length threshold Form a unified sentence length, use the pre-trained word vector table to obtain the vectorized representation of each word in the input text, and form a continuous and dense real vector matrix;
[0027] Step 2. For the input sentence word vector, a forward LSTM network is used to learn the above information of each word and a reverse LSTM network is used to learn the following information of each word, and the learning results are serially merged, so as to include ...
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 method of a mixed long-term short-term memory network and a convolutional neural network. By fully combining the advantages of the two-way long-term short-term memory network in learning the context information of the text and the convolutional neural network in learning the local features of the text Advantages: After using the bidirectional long-term and short-term memory network to learn the context information of the words, the convolutional neural network is used to further learn the local features of the word vectors that extract the context information, and then the bidirectional long-term short-term memory network is used to learn the context of these local features to form a fixed Dimension output, and finally through a multi-layer perceptron for classification output. It can further improve the accuracy of model classification, and has good versatility, and has achieved good results on multiple corpora tested.
Description
technical field [0001] The invention relates to the field of natural language processing, in particular to a text classification method of a hybrid long-short-term memory network and a convolutional neural network. Background technique [0002] Automatic text classification based on machine learning is the most popular research direction in the field of natural language processing in recent years. and in-depth applications. The so-called automatic text classification refers to the process of automatically determining the text category after analyzing the content of the text by using machine learning under the premise of a given classification system. Before the 1990s, automatic text classification was mainly based on knowledge engineering, that is, manual classification by professionals, and its disadvantages were high cost, time-consuming and labor-intensive. Since the 1990s, many researchers have begun to apply various statistical methods and machine learning methods 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 Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35G06N3/04G06N3/08
CPCG06F16/35G06N3/08G06N3/045
Inventor 苏锦钿霍振朗欧阳志凡
Owner SOUTH CHINA UNIV OF TECH