2022 2nd International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2022)
Home
Prof. Du Jinlian

Prof. Du Jinlian

Prof. Du Jinlian

杜金莲.jpg

Prof. Du Jinlian

Beijing University of Technology, China


Speech Title: Chinese Word Segmentation in Electronic Medical Record Text via Graph Neural Network

Abstract

Electronic medical record (EMR) text word segmentation is an important part of the construction of the intelligent medical system and is the basis of medical natural language processing. Due to the characteristics of EMR, such as strong specialization, high cost of annotation, special writing style and sustained growth of terminology, the current Chinese word segmentation (CWS) methods cannot fully meet the requirements of the application of EMR. In order to solve this problem, an EMR word segmentation model based on Graph Neural Network (GNN), bidirectional Long Short-Term Memory network (Bi-LSTM) and conditional random field (CRF) are designed in this paper to improve the segmentation effect and reduce the dependence on data set. Firstly, the model uses GNN based on the domain lexicon to learn the local composition features, such as word formation rules of medical terminology. Then the Bi-LSTM is introduced to capture the long-term dependence and context sequence information. Finally, CRF is used to obtain the optimal annotation sequence based on the sentence-level label information. Based on this multi-feature interaction, the ambiguity resolution and new word recognition in the EMR word segmentation are effectively carried out. Compared with CWS tools such as Jieba and Pkuseg, as well as benchmark models and state-of-the-art methods, the precision and recall rate of the model in this paper have been significantly improved.


Biography

Graduated from Dalian University of Technology with a doctorate in computer application. Over the years, has been engaged in research and development in the fields of data analysis, 3D modeling and simulation, real-time graphics rendering and mobile applications, presided over and participated in a number of provincial and ministerial scientific research projects. In the field of medical text information processing, including post-structured information processing methods of medical data, model construction and knowledge expression. The research work puts forward a systematic scheme for the construction of EMR knowledge map.