Chinese named entity recognition method based on multilevel residual convolution and attention mechanism

Abstract

The invention discloses a Chinese named entity recognition method based on multilevel residual convolution and an attention mechanism, and belongs to the field of natural language processing. According to the method, a multi-level residual convolutional network of a joint attention mechanism is adopted. In order to solve the problem that the model efficiency is low when a traditional recurrent neural network processes sequence information, multi-stage residual convolution is introduced to obtain local context information in different ranges, the computing power of hardware is fully utilized, and the model efficiency is remarkably improved. In addition, the recurrent neural network cannot effectively acquire global context information due to gradient disappearance and gradient explosion problems, so that the performance of the network is greatly influenced. According to the method, an attention mechanism is introduced into the network, and the importance weight of each character is calculated by constructing the relationship between each character and the sentence, so that global information is learned. Finally, the transition probability of the character tag is calculated by using the conditional random field to obtain a reasonable prediction result, and the robustness of the named entity recognition model is further improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to a Chinese named entity recognition method based on multi-level residual convolution and attention mechanism. Background technique [0002] Named entity recognition has always been the focus of natural language processing research, and its main goal is to identify entities such as person names, place names, and organization names from text. As a basic task in NLP (Natural Language Processing, Natural Language Processing), named entity recognition plays an important role in tasks such as automatic question answering and relationship extraction. At present, Chinese named entity recognition is mainly divided into two types of methods based on words and characters. Since entities mostly appear in the form of words, word-based methods can make full use of word information for entity recognition, but words need to be obtained from sentences through word segmentation, and the ...

AI Technical Summary

Problems solved by technology

Although the recurrent neural network can make full use of historical information and future information to process current information, it still faces the following problems: (1) How to make the model obtain more semantic information without introducing complex external knowledge

Images