An entity-relationship joint extraction method for medical text

Abstract

The invention discloses a medical text-oriented entity relationship joint extraction method. The method includes reorganizing the medical text entity relationship data set according to the triple mode, vectorized representation of the medical text sentence, using a bidirectional long short-term memory network to add automatic The attention mechanism builds the parameter sharing layer, uses the softmax function to predict the label of the head entity, uses CNN-softmax for joint decoding of the relationship-tail entity, combines the prediction results of the head entity to enhance the joint decoding representation, and uses the joint loss function optimization method to train the parameter sharing layer and joint decoding. decoding layer. The invention solves the problems of uneven distribution of entities and relation categories and positions in medical texts and multiple pairs of relations appearing in the same sentence at the same time, and can improve the quality and efficiency of entity relation extraction in medical texts.

Description

technical field [0001] The invention belongs to the technical field of medical text entity recognition, and in particular relates to a medical text-oriented entity relationship joint extraction method. Background technique [0002] With the rapid development of natural language processing technology, especially the continuous application in vertical fields, the transition of my country's medical services from "informatization" to "intelligence" has been greatly promoted. Extracting structured knowledge from free medical texts such as electronic medical records and biomedical documents is the basis for smart medical applications such as intelligent guidance, consultation, and clinical decision-making, and is also an important research content for building a medical knowledge map. Joint extraction of entities and relationships is one of the core tasks of information extraction, which specifically refers to automatically identifying the location, range and category of entities ...

AI Technical Summary

Problems solved by technology

[0007] (1) The error transmission problem caused by the pipeline entity and relation extraction method;

[0008] (2) The information sparse problem of multiple entities and multiple relationships in the same sentence;

[0009] (3) Insufficient interaction between the entity extraction module and the relationship extraction module in the joint extraction framework

Images