Research on Named Entity Recognition of Doctor-Patient Question Answering Community Based on BiLSTM-CRF Model
Zhikang Wang, Hua Guan · 2020
As more and more patients choose online consultation, the information in the Question and Answering(Q&A) community is widely studied. Through automatic extraction of medical inquiry information entities, and establishing a neural network model, the input of basic patient information and disease information can be extracted. In order to provide an effective method for exploring medical named entity recognition in the medical community. Entity annotation is performed for the medical community Q&A pairs, and a BiLSTM-CRF network model is established for training to realize the identification of medical entities which are crawled from Q&A community. This paper introduces the principles and process of BiLSTM-CRF model, illustrates our experiment, including the data sources, experiment environment, evaluation index. This paper chooses four models of HMM, CRF, BiLSTM and BiLSTM-CRF for experiments. Finally, the experimental results are compared which verifies the effectiveness of the BiLSTM-CRF model. Realizing the recognition and extraction of diabetes-related entities in the medical field.