癫痫病相关论文多模态知识图谱的构建初探  

Construction of Multi-Modal Knowledge Graph for Epilepsy Related Papers

作　　者：李星原 汪鹏[1] 申牧 李蕾[1] 张琳[1] LI Xingyuan;WANG Peng;SHEN Mu;LI Lei;ZHANG Lin(School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京邮电大学人工智能学院,北京100876

出　　处：《北京邮电大学学报》2022年第4期19-24,共6页Journal of Beijing University of Posts and Telecommunications

基　　金：北京市科学技术委员会项目(Z181100001018035);国家自然科学基金项目(61971056);北京市自然科学基金项目(4192040);教育部信息网络工程研究中心项目。

摘　　要：癫痫病相关论文缺乏命名实体识别和关系抽取任务的标注数据,命名实体识别和关系抽取模型无法用常规方法训练。为解决该问题,针对癫痫病相关论文的数据特点,改进了命名实体识别和关系抽取模型,提出利用相近领域的医疗数据和预训练模型构建零资源癫痫病领域命名实体识别和关系抽取模型。评估了现有无监督和半监督模型在癫痫病领域论文数据集上的性能,并针对数据集特征引入域对抗网络和关系判别器,有效地提高了命名实体识别和关系抽取模型的性能。将癫痫患者的脑电特征以视觉模态嵌入知识图谱中,在提高脑电分析可解释性的同时,构建了更加直观的多模态知识图谱。The performance of the existing named entity recognition and relation extraction models would sharply decline due to the lack of a large amount of annotated data for epilepsy-related papers. To solve this issue, a zero-resource named entity recognition and relation extraction model in the epilepsy domain is proposed based on medical data and a pre-training model from similar domains. The performance of the existing unsupervised and semi-supervised models on the epilepsy paper data set isevaluated, and then a domain adversarial network and a relation discriminator are introduced based on the characteristics of the data set to effectively improve the construction effect of the epilepsy domain knowledge graph. Electroencephalography(EEG) features of epilepsy patients are embedded into the knowledge graph in a visual modality. While improving the interpretability of EEG analysis, it builds a more intuitive multi-modal knowledge graph.

关 键 词：知识图谱 命名实体识别 关系抽取 癫痫 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]