Text classification method based on cyclic convolution network

Abstract

The invention discloses a text classification method based on a cyclic convolution network. The text classification method comprises the following steps: step 1, representing context vectors of all words by using a bidirectional cyclic network; step 2, combining the context vectors and a word vector of a current word into the representation of the current word; step 3, extracting the most important context information by using a maximum pool technology to obtain text representation; step 4, carrying out text classification by using the text representation. According to the method disclosed by the invention, more word order information in a text can be kept and a long-distance text dependence relation is captured; semantics of the words can be accurately described and the words and phrases, which have the greatest influences on the text classification, are found by the maximum pool technology, so that the text classification accuracy rate is effectively improved. A test shows that the efficiency of the method is averagely improved by 1% on the aspect of a plurality of text classification data sets.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a text classification method based on a circular convolution network. Background technique [0002] Text classification technology is an important technology in natural language processing, and it is a key step in tasks such as web page retrieval, sentiment analysis, and spam identification. The goal of text classification is to give a set of classified texts, use these texts to learn a classification method, and classify other texts into known categories. [0003] The key issue in text classification is feature representation, and the most commonly used feature representation method is the bag-of-words model. In the bag of words model, the most commonly used features are words, binary phrases, multivariate phrases (n-grams), and some manually extracted template features. After feature representation, traditional models often use methods such as word frequen...

AI Technical Summary

Problems solved by technology

For example, when a recurrent neural network constructs text semantics, it needs to first construct a tree structure. This step may depend on the accuracy of the syntax tree; In fact, not all the key information of the text is in the last part; the convolutional neural network needs to manually set a window to capture the context information when constructing the text semantics, but the classification result is sensitive to the size of the window. If the window is too small, the reserved Word order information and context dependencies will be insufficient. If the window is too large, a lot of noise will be introduced, which will adversely affect the results

Images