The Model based on UNILM of question conditional generation in the field of Chinese medicine

Corresponding author: shang xin, 2899870779@qq.com

DOI: 10.12201/bmr.202110.00036

•  

  Abstract: This paper focuses on the task of generating conditional text corresponding to questions or question groups forparagraphs or sentences and their related answers in the field of Chinese medicine. Traditional methods mainly use recurrentneural network for modeling, but these methods have many problems: (1) Low accuracy; (2)The parallelism is poor; (3)Relatively serious exposure deviation and repetitive generation problems; (4) A serious long-term dependency problem.Some recent advanced models are difficult to reproduce due to the lack of Chinese pre-training resources and computingresources. To solve these problems, we propose a conditional generation model based on UNILM, meanwhile, we add twoadditional embedding layers, copy mechanism, confrontation training and other modules to the base model. Under thecondition of single base model, no beam search and no case sensitivity, we achieved the second place (63.56%, while thefirst place got 63.79%) in the Challenge of TCM Literature Question generation on Tianchi platform, and it still has a largeroom for improvement.

  Key words: question generation; Unified Language Model Pre-training for Natural Language(UNILM); copy mechanism; adversarial training

  Submit time: 7 April 2022

  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

• kangyishuai, shaochenjie. An Algorithm for Generating TCM Document Questions Based on Unified Language Model. 2022. doi: 10.12201/bmr.202110.00044

  xie jia qi. Leveraging Pre-trained Language Model for Consumer Health Question Classification. 2021. doi: 10.12201/bmr.202101.00017

  jia lirong. research on question understanding about the automatic question answering system of TCM. 2021. doi: 10.12201/bmr.202101.00002

  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

  Yufan Zhu, Xin Zhao, Zhiqiang Yang, Houcheng Zhong, Lin Cai, Yuanlong Xie. Prospect of the Training Model for Artificial Intelligence + Medicine Inter-disciplinary Talents. 2020. doi: 10.12201/bmr.202008.00010

  Xiang Haiping, Xiao Li, Xu Chi. Building unified term service based on FHIR term component. 2021. doi: 10.12201/bmr.202107.00005

  HU Haiyang, ZHAO Congpu, Ma Lian, JIANG Huizhen, ZHANG Jing, ZHU Weiguo. Attention Mechanism And Dilated Convolution Neural Networks for Named Entity Recognition. 2021. doi: 10.12201/bmr.202102.00004

  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

  sunhaishu, gaohongjie. Design and Implementation of TCM Technology Intervention Platform for Insomnia based on Structural Equation Modeling. 2021. doi: 10.12201/bmr.202103.00001

  Zhai Xing, Li Guoliang, Guo Fengying. Research on the construction of the course system of big data management and application in traditional Chinese medicine Universities——An exploratory analysis based on the needs of College Students. 2020. doi: 10.12201/bmr.202008.00008

• ID	Submit time	Number	Download
  2	2022-03-31	bmr.202110.00036V2	Download
  1	2021-10-31	bmr.202110.00036V1	Download

• Public  Anonymous  To author only Submit Comments