摘要
[目的/意义]在新冠疫情背景下,提出多任务环境下融合迁移学习的疫情新闻要素识别方法,向公众提供面向应急事件的知识服务。[方法/过程]首先,通过多任务识别新闻要素:基于规则识别时间要素;并融合模型迁移与深度学习方法,构建跨领域的要素识别模型。在此基础上,构建疫情新闻要素的关联数据,以知识图谱的方式展示各要素之间的关联关系。[结果/结论]实验结果表明,除药物外的新闻要素的识别F1值均在80%以上,说明融合迁移学习的模型能够取得较优的识别效果;并且,关联数据知识图谱能够直观显示新闻的重点要素及新闻的主要内容。综上所述,提出的方法能够有效识别新冠疫情新闻要素,从而帮助新闻读者准确、高效地获取新闻中的重要信息。
[Purpose/significance]Under the background of novel coronavirus pneumonia,this paper proposes a method of identifying COVID-19 news elements in multi-task environment based on transfer learning to provide knowledge services of emergency for the public.[Method/process]Firstly,multiple tasks were used to identify news elements:Time elements were identified based on rules;besides,a cross domain element recognition model was constructed by integrating model transfer and deep learning methods.On this basis,the associated data of COVID-19 news elements was constructed,and the relationship between the elements was displayed by knowledge mapping.[Result/conclusion]The experimental results show that the F1 values of news elements except Drug are above 80%,which indicates that the transfer learning model can achieve fine recognition effect.Moreover,the knowledge map of associated data can intuitively display the key elements and main contents of news.In conclusion,the method proposed in this paper can effectively identify elements in COVID-19 news,thus it can help readers obtain important information from the news accurately and efficiently.
作者
赵梓博
王昊
刘友华
张卫
孟镇
Zhao Zibo;Wang Hao;Liu Youhua;Zhang Wei;Meng Zhen(School of Information Management,Nanjing University,Nanjing 210023;Jiangsu Key Laboratory of Data Engineering and Knowledge Service,Nanjing 210023)
出处
《知识管理论坛》
2021年第1期2-13,共12页
Knowledge Management Forum
基金
国家社会科学基金重大招标项目“情报学学科建设与情报工作未来发展路径研究”(项目编号:17ZDA291)
南京大学博士研究生创新研究项目“基于知识图谱的医学信息挖掘与推荐研究”(项目编号:CXYJ21-69)研究成果之一
江苏青年社科英才和南京大学仲英青年学者等人才培养计划的支持
关键词
多任务
迁移学习
新冠
新闻要素识别
命名实体识别
冷启动
multi-task
transfer learning
COVID-19
news elements identification
named entity recognition
cold start
