Text sentiment analysis method based on word vector deformation and bidirectional bit order convolution

Abstract

The invention discloses a text sentiment analysis method based on word vector deformation and bidirectional bit order convolution, which comprises the following steps: obtaining an evaluation statement, inputting the evaluation statement into a trained bidirectional standard convolution network model with bit order information, and outputting a text sentiment analysis result through the model; wherein the bidirectional standard convolutional network model with bit sequence information comprises a word embedding layer, a bit sequence information layer, a word vector deformation layer, a convolutional layer, a double-end structure and a classification layer; the word embedding layer is used for converting words in an evaluation statement into word vectors which can be understood by a computer; the bit sequence information layer is used for adding bit sequence information to the word vector to obtain the word vector with the bit sequence information; the word vector deformation layer is used for deforming word vectors into word block matrixes and finally splicing the word block matrixes into sentence matrixes; the convolution layer is used for performing convolution operation on the sentence matrix to obtain word vector features; and the classification layer is used for carrying out classification operation on the spliced word vector features to obtain a final text sentiment analysis result.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a text sentiment analysis method based on word vector deformation and bidirectional sequence convolution. Background technique [0002] At present, there are still the following problems in the use of convolution by neural network models in sentiment classification tasks: [0003] (1) The size of the convolution kernel is usually n*D, n is the number of word vectors calculated by the convolution kernel at one time, and D is the word vector dimension. The dimension of word vector is usually 200 to 500, so the convolution kernel is too large, resulting in huge parameters. [0004] (2) The convolution is performed in the form of a sliding window, and the semantic information of adjacent words can be captured in each convolution, but the semantic information between words with a long distance cannot be captured. SUMMARY OF THE INVENTION [0005] The purpose of the prese...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a text sentiment analysis method based on word vector deformation and bidirectional bit sequence convolution, in order to solve the existing problems of neural network in the existing sentiment classification task

Images