Iterative Entity Alignment via Re-Ranking
-
摘要: 现有的知识图谱无法避免地存在不完整这一问题.缓解此问题的可行方法是引入外部知识图谱中的知识.在此过程中,实体对齐是最关键的步骤.当前最先进的实体对齐解决方案主要依靠知识图谱的结构信息来判断实体的等价性,但在真实世界知识图谱上,大部分实体只具有较低的节点度数以及微少的结构信息.此外,标注数据的缺乏也大大限制了实体对齐模型的效果.为解决上述问题,提出将不受节点度数影响的实体名信息与结构信息相结合,从更全面的角度实现实体对齐.在此基本框架上,利用基于课程学习的迭代训练方法从易至难地选择高置信度结果加入到训练数据中,扩增标注数据的规模.最后使用词移距离模型进一步改进实体名信息的利用方式,并对前序对齐结果重排序,提升实体对齐准确率.在跨语言以及单语言实体对齐任务上的实验结果表明,提出的实体对齐方法性能远好于当前最好的方法.Abstract: Existing knowledge graphs (KGs) inevitably suffer from the problem of incompleteness. One feasible approach to tackle this issue is by introducing knowledge from other KGs. During the process of knowledge integration, entity alignment (EA), which aims to find equivalent entities in different KGs, is the most crucial step, as entities are the pivots that connect heterogeneous KGs. State-of-the-art EA solutions mainly rely on KG structure information for judging the equivalence of entities, whereas most entities in real-life KGs are in low degrees and contain limited structural information. Additionally, the lack of supervision signals also constrains the effectiveness of EA models. In order to tackle aforementioned issues, we propose to combine entity name information, which is not affected by entity degree, with structural information, to convey more comprehensive signals for aligning entities. Upon this basic EA framework, we further devise a curriculum learning based iterative training strategy to increase the scale of labelled data with confident EA pairs selected from the results of each round. Moreover, we exploit word mover’s distance model to optimize the utilization of entity name information and re-rank alignment results, which in turn boosts the accuracy of EA. We evaluate our proposal on both cross-lingual and mono-lingual EA tasks against strong existing methods, and the experimental results reveal that our solution outperforms the state-of-the-arts by a large margin.
-
Keywords:
- entity alignment /
- curriculum learning /
- iterative training /
- re-ranking /
- knowledge graph alignment
-
-
期刊类型引用(10)
1. 杜金明,孙媛媛,林鸿飞,杨亮. 融入知识图谱和课程学习的对话情绪识别. 计算机研究与发展. 2024(05): 1299-1309 . 本站查看
2. 纪鑫,武同心,王宏刚,杨智伟,何禹德,赵晓龙. 基于多通道图神经网络的属性聚合式实体对齐. 北京航空航天大学学报. 2024(09): 2791-2799 . 百度学术
3. 陈富强,寇嘉敏,苏利敏,李克. 基于图神经网络的多信息优化实体对齐模型. 计算机科学. 2023(03): 34-41 . 百度学术
4. 刘璐,飞龙,高光来. 基于多视图知识表示和神经网络的旅游领域实体对齐方法. 计算机应用研究. 2023(04): 1044-1051 . 百度学术
5. 安靖,司光亚,周杰,韩旭. 基于知识图谱的仿真想定智能生成方法. 指挥与控制学报. 2023(01): 103-109 . 百度学术
6. 孙泽群,崔员宁,胡伟. 基于链接实体回放的多源知识图谱终身表示学习. 软件学报. 2023(10): 4501-4517 . 百度学术
7. 时慧芳. 融合高速路门机制的跨语言实体对齐研究. 现代电子技术. 2023(20): 167-172 . 百度学术
8. 张富,杨琳艳,李健伟,程经纬. 实体对齐研究综述. 计算机学报. 2022(06): 1195-1225 . 百度学术
9. 姜亚莉,戴齐,刘捷. 基于交叉图匹配和双向自适应迭代的实体对齐. 信息与电脑(理论版). 2022(20): 201-204 . 百度学术
10. 王小鹏. 基于知识图谱的择优分段迭代式实体对齐方法研究. 信息与电脑(理论版). 2021(18): 48-52 . 百度学术
其他类型引用(15)
计量
- 文章访问数: 1135
- HTML全文浏览量: 3
- PDF下载量: 367
- 被引次数: 25