摘要
实体消歧(entity disambiguation)是指将文档中识别出的实体指称(entity mention)链向其在特定知识库中相应条目的过程。该文结合主流的基于深度学习的实体消歧方法并融合实体知识描述展开了实验性研究。实验结果表明,融合实体知识描述的实体消歧方法在公开数据集上取得了与已有最好算法相当的F1性能。
Entity disambiguation is the process of linking recognized entity mentions to its corresponding entry in a particular knowledge base.This paper combines the mainstream deep learning-based entity disambiguation method and the entity knowledge description.Experiments demonstrate that the proposed method obtains competitive or state-of-the-art F1 at public datasets.
作者
范鹏程
沈英汉
许洪波
程学旗
廖华明
FAN Pengcheng;SHEN Yinghan;XU Hongbo;CHENG Xueqi;LIAO Huaming(CAS Key Laboratory of Network Data Science&Technology,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《中文信息学报》
CSCD
北大核心
2020年第7期42-49,78,共9页
Journal of Chinese Information Processing
基金
国家重点研发计划(2017YFB1002302)
关键词
实体消歧
深度学习
注意力机制
entity disambiguation
deep learning
attention mechanism
