Attention Mechanism And Dilated Convolution Neural Networks for Named Entity Recognition

Corresponding author: ZHU Weiguo, zhuwg@pumch.cn

DOI: 10.12201/bmr.202102.00004

•  

  Abstract: Named entity recognition is the most basic and important step of medical natural language processing task. The performance of the model based on word vector embedding is easily affected by the effect of word segmentation. Moreover, most of the existing models use recurrent neural network, which has slow calculation speed and is difficult to meet the requirements of practical application.To solve the above problems, this paper constructs a named entity recognition model based on multi attention mechanism and expansion convolution neural network, which reduces the dependence of the model on word segmentation effect through word embedding and position embedding algorithm; using expansion convolution neural network model for training can better understand the semantic information and improve the calculation speed. At the same time, experiments were designed to compare the results with other named entity methods, such as bi-directional long-term and short-term memory network model. By comparing the F1 scores of experimental results, the proposed model improved by 3.42% compared with bilstm baseline model, 2.66% compared with bilstm + CNN model, and 2.66% compared with bilstm + attention + CNN model The model is improved by 2.04%. Experiments show that the proposed model achieves better named entity recognition effect.

  Key words: Named Entity Recognition; Dilated Convolution Neural Networks; Word embedding; NLP

  Submit time: 9 March 2021

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• wuxuehong. A method of recognizing entities from Chinese Electronic Medical Record based on domain word vector combined with word attributes reasoning. 2021. doi: 10.12201/bmr.202109.00016

  Zhang Chunyang, Hu Hongwei. Research on the prediction mechanism of working ability of elderly nursing staff based on neural network: Perspective of professionalization. 2021. doi: 10.12201/bmr.202104.00022

  pangzhen, GuJiYu, WuYuFei, YanSshiXing, LiWangYang, SunYue. A study on the solution of the problem of extracting essential substance of TCM diagnosis and treatment of hypertension based on triple extraction strategy. 2021. doi: 10.12201/bmr.202107.00015

  Li Xiaoying, Cai Miaozhi, Li Junlian, Ren Huiling, Ji Yujing, Deng Panpan, Xia Guanghui. Research on the construction of COVID-19 knowledge graph for literature organization. 2020. doi: 10.12201/bmr.202010.00840

  duxuejie, gehui. Study on the design of prediction and early warning model of hand, foot and mouth disease based on BP neural network.. 2021. doi: 10.12201/bmr.202102.00002

  GUO ZheTao, SHI Wenli, YANG Tao. Design and implementation of intelligent speech assistant for clinical diagnosis and treatment of traditional Chinese medicine based on speech recognition. 2021. doi: 10.12201/bmr.202110.00013

  Zhu Xiaoxiao, Qian Aibing. Analysis of Network Attention Characteristics of Breast Cancer Prevention and Treatment Health Information Based on Baidu Index. 2020. doi: 10.12201/bmr.201906.00001

  Guo Yi, Jiang Tao, Hu Yingying, Tang Guangming. The Design and Application of Performance Assessment Information System for Primary Health Care Institutions Compensation Mechanism Reform. 2020. doi: 10.12201/bmr.201909.00001

  Luxinyi, Wangyadong. The construction of the comprehensive regulation system of the medical and health industry :a qualitative analysis based on the grounded theory. 2021. doi: 10.12201/bmr.201910.00001

  chen ling, Zhang Hongwei, Wang Chunmei. Research on the Construction of Medical Wisdom Library from the Perspective of Modern Public Cultural Service. 2020. doi: 10.12201/bmr.201911.00001

• ID	Submit time	Number	Download
  1	2021-02-17	bmr.202102.00004V1	Download

• Public  Anonymous  To author only Submit Comments