Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (11): 129-138.DOI: 10.3778/j.issn.1002-8331.2302-0246

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Named Entity Recognition for Mine Electromechanical Equipment Monitoring Text

QIU Yunfei, XING Haoran, YU Zhilong, ZHANG Wenwen   

  1. 1.School of Software, Liaoning Technology University, Huludao, Liaoning 123105, China
    2.School of Business Administration, Liaoning Technology University, Huludao, Liaoning 123105, China
  • Online:2024-06-01 Published:2024-05-31

面向矿山机电设备监测文本的命名实体识别

邱云飞,邢浩然,于智龙,张文文   

  1. 1.辽宁工程技术大学 软件学院,辽宁 葫芦岛 123105
    2.辽宁工程技术大学 工商管理学院,辽宁 葫芦岛 123105

Abstract: The correct extraction of equipment name, parameter standard, fault location, fault type and other entities in the monitoring text of mine electromechanical equipment can assist experts to find abnormal equipment as soon as possible and improve the efficiency and accuracy of equipment fault analysis. In view of the fact that most entities in the field of mine electromechanical equipment are nested entities with long characters and strong contextual relevance, an entity recognition method combining multi-granularity features is proposed in this paper. The long sequence nested entity boundary is initially determined by the machine reading comprehension framework, and the context association representation between entities is deeply explored by BiLSTM neural network integrating attention mechanism. The experimental results show that this method has a good recognition effect on the entities in the mine electromechanical equipment monitoring text, and improves the effectiveness of other named entity recognition tasks in low resource scenarios.

Key words: mining electromechanical equipment, named entity recognition, multi-granularity information, machine reading and comprehension

摘要: 正确抽取矿山机电设备监测文本中的设备名称、参数标准、故障位置、故障类型等实体,可以辅助专家尽早发现异常机电设备、提升分析设备故障的效率和精度。针对矿山机电设备领域实体多为嵌套实体,且具备字符较长、上下文关联性较强等特点,提出一种联合多粒度特征的实体识别方法,通过机器阅读理解框架初步确定长序列嵌套实体边界,采用融合注意力机制的BiLSTM神经网络深挖实体间上下文关联。实验结果表明,该方法对矿山机电设备监测文本中的实体具备较好的识别效果,并且提升了其他低资源场景下命名实体识别任务的效果。

关键词: 矿山机电设备, 命名实体识别, 多粒度信息, 机器阅读理解