A drug entity relationship extraction method and system based on an attention mechanism neural network

Abstract

The invention relates to a drug entity relationship extraction method and system based on an attention mechanism neural network. The method comprises the following steps: (1) analyzing the text content of a pharmaceutical document, using sentences as basic units for sentence segmentation, and performing vectorization representation on each word in the sentences; (2) inputting a vectorized representation result into a recurrent neural network, extracting association characteristics of words in the sentences according to a front-back bidirectional word sequence through the recurrent neural network, and identifying all medicine entities; (3) obtaining inter-word importance weights in the sentences through an attention mechanism neural network, and combining the inter-word importance weights with the output in the step (2); And (4) inputting a result obtained in the step (3) into a convolutional neural network, and predicting a category relation between every two medicated entity words through the convolutional neural network. According to the classification method for increasing the attention mechanism concerned entity class information weight, the influence caused by wrong dependencyanalysis results in long sentences can be reduced, and the accuracy of extracting the pharmacochemical entity relationship is improved.

Description

technical field [0001] The invention belongs to the field of natural language processing and relates to an information extraction technology, in particular to a method and system for extracting drug entity interaction relations in medicinal chemistry documents. Background technique [0002] The extraction of medicinal chemistry entity relationship is the basic task in the construction of medicinal chemistry knowledge base. The built system automatically extracts the relationship between entities from the literature, which provides more important reference value for disease treatment, drug development, and life science research. The construction and maintenance of medicinal chemistry knowledge databases provide deeper information. Entity relationship extraction is the cornerstone of medicinal chemistry knowledge acquisition, in order to build a knowledge base to improve the cognitive level of medicinal chemistry phenomena. [0003] Since the relationship between medicinal an...

AI Technical Summary

Problems solved by technology

[0007] Practice has shown that the rule-based method is not effective in extracting complex relationships from long sentences, and the literature in the field of pharmaceutical chemistry contains a large number of long sentences with complex structures such as appositions and parallel structures; making rules is time-consuming and labor-intensive and requires the participation of professional personnel; In addition, it is difficult for human-crafted rules to cover all application text scenarios

Existing research focuses on methods based on supervised machine learning. This type of method has good performance and portability, but the method relies on external natural language processing tools. If the external tool makes a mistake, it will cause error propagation and affect performance.

Images