Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (21): 14-23.DOI: 10.3778/j.issn.1002-8331.2103-0469

Previous Articles     Next Articles

Review of Deep Learning-Based Biomedical Entity Relation Extraction Research

WEI Hao, ZHOU Ai, ZHANG Yijia, CHEN Fei, QU Wen, LU Mingyu   

  1. School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China
  • Online:2021-11-01 Published:2021-11-04

深度学习生物医学实体关系抽取研究综述

隗昊,周爱,张益嘉,陈飞,屈雯,鲁明羽   

  1. 大连海事大学 信息科学技术学院,辽宁 大连 116026

Abstract:

With the development of life science and technology, the literature in the field of biomedicine has grown exponentially. How to excavate and extract valuable information from massive literature has become a new research opportunity in the field of biomedicine. As the core technology of information extraction, named entity recognition and relationship extraction become the basis and key of biomedical text mining. Its main work is to identify the entities in the biomedical text and extract the biomedical semantic relations between the entities. This paper aims to summarize the deep learning-based methods of entity identification and relationship extraction in biomedical field. It comprehensively expounds the development process of various technologies from the perspectives of concept, progress and status quo, and further clarifies the exploration direction of biomedical text information extraction.

Key words: biomedical, information extraction, named entity recognition, relation extraction, deep learning

摘要:

随着生命科学技术的发展,生物医学领域文献呈指数级增长,如何从海量文献中挖掘、抽取有价值的信息成为生物医学领域新的研究契机。作为信息抽取的核心技术,命名实体识别和关系抽取成为生物医学文本挖掘的基础和关键,其主要工作为识别生物医学文本中的实体,并提取实体间存在的生物医学语义关系。当前深度学习技术在各领域自然语言处理任务中取得了长足的发展,旨在总结基于神经网络的生物医学实体识别和关系抽取的方法,从概念、进展、现状等多角度全面阐述各项技术在生物医学领域的发展历程,进一步明确生物医学文本信息抽取工作的探索方向。

关键词: 生物医学, 信息抽取, 命名实体识别, 关系抽取, 深度学习