Text word vector model training method, electronic equipment and computer storage medium

Abstract

The invention relates to the technical field of computer processing, and discloses a training method of a text word vector model, electronic equipment and a computer readable storage medium. The training method of the text word vector model comprises the steps: determining a sub-model corresponding to each training statement according to statement tags included in each training statement, the statement tags being used for indicating the sub-models corresponding to the training statements; Respectively training the corresponding semantic word vector quantum model and the text classification sub-model through each training statement to update a first word vector matrix of the text word vector model, so as to train the text word vector model by updating the first word vector matrix. Accordingto the method provided by the embodiment of the invention, through the combination of the semantic word vector quantum model and the text classification sub-model, the close connection and fusion between the word vector training method and the text classification method are realized, and the representation capability of the word vector is enhanced.

Description

technical field [0001] The present application relates to the technical field of computer processing, and in particular, the present application relates to a training method of a text word vector model, electronic equipment and a computer storage medium. Background technique [0002] In recent years, word vectors have become more and more widely used in the field of natural language processing, such as part-of-speech tagging, sentiment classification, text classification, keyword extraction and semantic similarity, etc. Word vector refers to the representation of converting a word or word into a one-dimensional vector. Common word vector training methods include word2vec (word vector), FastText (fast text), etc. [0003] Text classification is to classify texts according to different categories (such as sports, entertainment, etc.), common methods for existing text classification, such as Bi-LSTM (bidirectional long-term short-term memory cycle neural network), Text-CNN (tex...

AI Technical Summary

Problems solved by technology

[0003] Text classification is to classify texts according to different categories (such as sports, entertainment, etc.). The existing common methods of text classification, such as Bi-LSTM (two-way long-term and short-term Memory cycle neural network), Text-CNN (text convolutional neural network) and other deep learning algorithms are generally suitable for labeled data with a small amount of data, and to a certain extent rely on the pre-training of word vectors, but the existing Word vector training methods, such as word2vec, FastText, etc., are suitable for large-scale corpus data, but they cannot be directly used for text classification because they are less distinguishable for words with similar contexts such as movies, TV dramas, directors, actors, etc., namely These words are relatively close after the word vector training, which leads to the problem that the connection between the two is not close when using the ordinary word vector training method to train the word vector, and then use the deep learning method for text classification learning.

Images