文章摘要
王 政 朱礼军 徐 硕.实体关系的弱监督学习抽取方法[J].中国科技资源导刊,2018,(2):103~110
实体关系的弱监督学习抽取方法
Review of Weakly Supervised Relation Extraction
投稿时间:2017-07-28  
DOI:
中文关键词: 弱监督学习;实体关系抽取;半监督学习;远程监督学习;无监督学习
英文关键词: weakly supervised learning, relation extraction, semi-supervised learning, distant supervised learning, unsupervised learning
基金项目:国家自然科学基金项目“基于论文和专利资源的技术机会发现研究”(71403255)。
作者单位
王 政 朱礼军 徐 硕 1. 中国科学技术信息研究所,北京 100038; 2. 北京工业大学经济与管理学院,北京现代制造业发展研究基地,北京 100124 
摘要点击次数: 1836
全文下载次数: 2531
中文摘要:
      许多相关综述工作往往侧重于通用领域的实体关系抽取,没有充分体现弱监督学习实体关系抽取的重要 性。文章立足于科技情报领域,在综述大量文献的基础上,剖析半监督、远程监督和无监督等3种弱监督实体关系抽取 方法的逻辑关系,并总结了各自的优缺点。基于弱监督学习的实体关系抽取方法可以部分解决标注数量不足的问题。 特别是,针对不同的科技情报应用,多种弱监督实体关系抽取方法的综合运用可以取得显著效果,但是精确度偏低的 问题在未来相当长的时间内仍然是弱监督学习实体关系抽取的主要挑战。
英文摘要:
      Although recent related reviews focused on general knowledge, they were unaware of the importance of weakly supervised relation extraction. So, on the basis of science and technology information domain, this work analyzed the logical relations among semi-supervised, distant supervised and unsupervised methods by reviewing, and the resulting advantages and disadvantages were summarized. It’s believed that weakly supervised learning could partially solve the scarcity of labeled data. Especially for specific technology information applications, integrated weakly supervised methods may make giant improvement. But in the near future, the main challenge for weakly supervised relation extraction is still the problem of precision.
查看全文   查看/发表评论  下载PDF阅读器
关闭

分享按钮