Entity relationship extraction method based on multi-convolution-window size attention convolutional neural network

Abstract

The invention provides an entity relationship extraction method based on a multi-convolution-window size attention convolutional neural network. According to the entity relationship extraction method,a convolutional neural network based on a convolutional window size attention mechanism is provided; and compared with a kernel method and a feature method, the relation classification task is more efficient, so that automatic feature extraction can be realized, and the defects of complicated feature engineering and corresponding error propagation can be avoided, and the n-gram information most important for relationship classification in sentences can be effectively concerned, and the accuracy of classification targets is improved, and compared with a neural network based on RNN and word embedding attention, the entity relationship extraction method has the advantages of relatively low complexity and high running speed.

Description

technical field [0001] The present invention relates to the field of Chinese entity relationship extraction, and more specifically, relates to a method for extracting entity relationship based on multi-convolution window size attention convolutional neural network. Background technique [0002] Entity relationship extraction is a key subtask of natural language processing tasks such as knowledge graphs, question answering systems, and retrieval systems. Entity relationship extraction tasks generally give a sentence containing two labeled entities, and then ask to predict the relationship between the two entities in this sentence. [0003] For this task, the current mainstream methods mainly include the following categories: The first category is the method based on feature extraction. [0004] This method usually requires the help of language analysis systems such as syntactic dependency trees, part-of-speech tagging, or natural language processing tools like word-Net to ma...

AI Technical Summary

Problems solved by technology

[0004] This method usually requires the help of language analysis systems such as syntactic dependency trees, part-of-speech tagging, or natural language processing tools like word-Net to manually extract features, which will cause the problem of error transmission, and also require a lot of manpower and time costs.

The second type of method is based on the kernel method. This method does not require tedious feature engineering work. Instead, it needs to design a suitable kernel function based on the syntax and dependency structure. Therefore, it still needs to use some natural language processing tools, so it also has errors. passing problem

However, in the currently proposed convolutional neural network models, many networks do not use multiple convolution window sizes to extract the n-gram features of the sentence, and the n-gram information of some key points of the sentence is very important for the entity relationship extraction task. , so when these features are ignored, the performance of the network may degrade

Images