A text classification algorithm that combines statistical features and Attention mechanism

Abstract

The invention relates to a text classification algorithm which combines statistical features and an Attention mechanism, and the Attention mechanism has been gradually applied to the field of naturallanguage processing. The prior method greatly increases the calculation amount when calculating the Attention weight value, and the invention proposes that the Attention weight value is calculated atthe structured event level. On the one hand, events contain richer semantics than words or phrases; On the other hand, the event-based Attention mechanism reduces computational complexity. At the sametime, statistical features are added to the calculation of Attention weights. Compared with the existing model, the semantic information contained in the event structure and the corresponding statistical features improve the quality of text vector representation and achieve better classification performance. The classification accuracy is evaluated, and the experimental results show that the model not only reduces the training time, but also achieves better results.

Description

technical field [0001] The invention relates to a novel text classification algorithm, especially for large text data sets, which reduces the time complexity of calculation while improving the classification accuracy. Background technique [0002] The rapid development of network and information technology has led to exponential growth of data. Text is the main form of Internet information expression. How to extract key and effective information from complicated text data is currently a research hotspot in the field of data mining. Text classification technology As a key technology in the field of data mining, text information can be preliminarily processed and classified. [0003] The main tasks of text classification are text representation, feature extraction, classification algorithm and effect evaluation. In order to be calculated and processed by the computer, the initial input text must first be represented by the corresponding feature extraction algorithm, and then ...

AI Technical Summary

Problems solved by technology

At the same time, in order to solve the problem that the existing deep learning model cannot learn text statistical features, statistical features are added on the basis of Attention weight calculation. Compared with the existing model, the semantic information contained in the event structure and the corresponding statistics features improve the quality of text vector representations and achieve better classification performance

Images