Automatic labeling method for professional vocabularies of medical documents

Abstract

The invention relates to an automatic labeling method for professional vocabularies of medical documents. which comprises the following steps: carrying out data preprocessing on an input medical document to obtain a preprocessed medical document text; obtaining and fusing the letter-level feature vectors, the word-level feature vectors and the language feature vectors of the words to serve as encoding vectors of the words; word annotations of the medical document text after word segmentation are classified to obtain an annotated data set; outputting a multi-dimensional vector for each word asa spatial representation of the word; obtaining an enhanced annotation data set; and performing training modeling, and finally outputting a marking result. method in design. A semi-supervised learning algorithm is adopted to label a large amount of unlabeled data so that the defect that the existing medical industry is too few in labeled data is successfully overcome. The amount of data capable of being used by the model is effectively increased. The labeling accuracy of the algorithm on keywords and professional vocabularies is greatly improved and the method can be widely applied to medicalliterature processing.

Description

technical field [0001] The invention belongs to the technical field of machine learning, in particular to an automatic tagging method for professional vocabulary in medical documents. Background technique [0002] As the medical research community grows, more and more papers are published every year. There is a growing need to find ways to improve papers and automatically understand the key ideas in those papers. However, relatively little scientific information has been extracted due to the wide variety of domains and extremely limited annotation resources. [0003] At the same time, as people's demand for medical resources, corresponding medical documents, and the number of cases surge, researchers and medical staff need to quickly sort out patients' past medical data. It is often some professional vocabulary or keywords that can quickly help medical staff to make judgments from patient cases. It takes a lot of time to manually sort out these vocabulary and keywords. Due...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose a method for automatic labeling of professional vocabulary in medical documents, which uses a semi-supervised learning algorithm to expand the amount of data, and overcomes the poor model performance caused by the lack of data in the previous medical text labeling problems, and finally improved the accuracy of identifying specialized vocabulary and key words in the text

Images