《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (6): 1793-1800.DOI: 10.11772/j.issn.1001-9081.2024050703
• 人工智能 • 上一篇
收稿日期:
2024-05-30
修回日期:
2024-07-30
接受日期:
2024-08-28
发布日期:
2024-09-09
出版日期:
2025-06-10
通讯作者:
黄妍
作者简介:
翟社平(1971—),男,陕西宝鸡人,教授,博士,CCF高级会员,主要研究方向:语义计算、区块链基金资助:
Sheping ZHAI1,2, Yan HUANG1(), Qing YANG1, Rui YANG1
Received:
2024-05-30
Revised:
2024-07-30
Accepted:
2024-08-28
Online:
2024-09-09
Published:
2025-06-10
Contact:
Yan HUANG
About author:
ZHAI Sheping, born in 1971, Ph. D., professor. His research interests include semantic computing, blockchain.Supported by:
摘要:
实体对齐(EA)旨在识别不同来源的知识图谱(KG)中指代相同的实体。现有的EA模型大多关注实体自身的特征,部分模型引入了实体的关系和属性信息辅助实现对齐,然而这些模型忽视了实体中潜在的邻域信息和语义信息。为了解决上述问题,提出一种融合三元组和文本属性的多视图EA模型(MultiEA)。所提模型将实体信息分为多个视图以实现对齐。针对缺少邻域信息的问题,采用图卷积网络(GCN)与翻译模型来并行学习嵌入实体的关系信息;针对缺少语义信息的问题,采用词嵌入与预训练语言模型学习属性文本的语义信息。实验结果表明,在DBP15K的3个子数据集上,相较于得到最优结果的基线模型EPEA(Entity-Pair Embedding Approach for KG alignment),所提模型的Hits@1值分别提升了2.18、1.36和0.96个百分点,平均倒数排名(MRR)分别提升了2.4、0.9和0.5个百分点,验证了所提模型的有效性。
中图分类号:
翟社平, 黄妍, 杨晴, 杨锐. 融合三元组和文本属性的多视图实体对齐[J]. 计算机应用, 2025, 45(6): 1793-1800.
Sheping ZHAI, Yan HUANG, Qing YANG, Rui YANG. Multi-view entity alignment combining triples and text attributes[J]. Journal of Computer Applications, 2025, 45(6): 1793-1800.
语言 | 实体数 | 关系数 | 属性数 | 关系三元组数 | 属性三元组数 |
---|---|---|---|---|---|
ZH | 66 496 | 2 830 | 8 113 | 153 929 | 379 684 |
EN | 98 125 | 2 317 | 7 173 | 237 674 | 567 755 |
FR | 66 858 | 1 379 | 4 547 | 192 191 | 528 665 |
EN | 105 889 | 2 209 | 6 422 | 278 590 | 576 543 |
JA | 65 744 | 2 043 | 5 882 | 164 373 | 354 619 |
EN | 95 680 | 2 096 | 6 066 | 233 319 | 497 230 |
表1 DBP15K数据集介绍
Tab. 1 DBP15K dataset introduction
语言 | 实体数 | 关系数 | 属性数 | 关系三元组数 | 属性三元组数 |
---|---|---|---|---|---|
ZH | 66 496 | 2 830 | 8 113 | 153 929 | 379 684 |
EN | 98 125 | 2 317 | 7 173 | 237 674 | 567 755 |
FR | 66 858 | 1 379 | 4 547 | 192 191 | 528 665 |
EN | 105 889 | 2 209 | 6 422 | 278 590 | 576 543 |
JA | 65 744 | 2 043 | 5 882 | 164 373 | 354 619 |
EN | 95 680 | 2 096 | 6 066 | 233 319 | 497 230 |
模型 | |||||||||
---|---|---|---|---|---|---|---|---|---|
Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | |
MTransE | 30.83 | 61.41 | 0.364 | 27.86 | 57.45 | 0.349 | 24.41 | 55.55 | 0.335 |
IPTransE | 40.60 | 73.50 | 0.516 | 36.70 | 69.30 | 0.474 | 33.30 | 68.50 | 0.451 |
JAPE | 41.18 | 74.46 | 0.490 | 36.25 | 68.50 | 0.476 | 32.39 | 66.68 | 0.430 |
AWUN | 75.10 | 88.30 | 0.796 | 80.50 | 92.40 | 0.848 | 91.50 | 0.938 | |
RDGCN | 70.75 | 84.55 | 0.746 | 76.74 | 89.54 | 0.812 | 88.64 | 95.72 | 0.911 |
NMN | 73.30 | 86.90 | — | 78.50 | 91.20 | — | 90.20 | 96.70 | — |
MultiKE | 50.90 | 57.60 | 0.523 | 39.30 | 48.90 | 0.426 | 63.90 | 71.20 | 0.665 |
RoadEA | 82.40 | 89.60 | 0.846 | 86.80 | 90.50 | 0.886 | 81.00 | 88.40 | 0.831 |
GALA | 78.10 | 86.24 | 0.811 | 82.80 | 90.73 | 0.855 | 92.70 | 96.97 | 0.942 |
RALG | 83.54 | 94.75 | 0.876 | 87.23 | 96.58 | 0.906 | 94.83 | 0.964 | |
EPEA | 98.60 | ||||||||
MultiEA | 90.68 | 97.43 | 0.935 | 93.76 | 97.83 | 0.951 | 96.46 | 98.73 | 0.972 |
表2 MultiEA模型与基线模型在DBP15K数据集上的实验结果对比
Tab. 2 Experimental results comparison of MultiEA model and baseline models on DBP15K dataset
模型 | |||||||||
---|---|---|---|---|---|---|---|---|---|
Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | |
MTransE | 30.83 | 61.41 | 0.364 | 27.86 | 57.45 | 0.349 | 24.41 | 55.55 | 0.335 |
IPTransE | 40.60 | 73.50 | 0.516 | 36.70 | 69.30 | 0.474 | 33.30 | 68.50 | 0.451 |
JAPE | 41.18 | 74.46 | 0.490 | 36.25 | 68.50 | 0.476 | 32.39 | 66.68 | 0.430 |
AWUN | 75.10 | 88.30 | 0.796 | 80.50 | 92.40 | 0.848 | 91.50 | 0.938 | |
RDGCN | 70.75 | 84.55 | 0.746 | 76.74 | 89.54 | 0.812 | 88.64 | 95.72 | 0.911 |
NMN | 73.30 | 86.90 | — | 78.50 | 91.20 | — | 90.20 | 96.70 | — |
MultiKE | 50.90 | 57.60 | 0.523 | 39.30 | 48.90 | 0.426 | 63.90 | 71.20 | 0.665 |
RoadEA | 82.40 | 89.60 | 0.846 | 86.80 | 90.50 | 0.886 | 81.00 | 88.40 | 0.831 |
GALA | 78.10 | 86.24 | 0.811 | 82.80 | 90.73 | 0.855 | 92.70 | 96.97 | 0.942 |
RALG | 83.54 | 94.75 | 0.876 | 87.23 | 96.58 | 0.906 | 94.83 | 0.964 | |
EPEA | 98.60 | ||||||||
MultiEA | 90.68 | 97.43 | 0.935 | 93.76 | 97.83 | 0.951 | 96.46 | 98.73 | 0.972 |
模型 | |||||||||
---|---|---|---|---|---|---|---|---|---|
Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | |
MultiEA-Name | 82.80 | 88.41 | 0.869 | 81.83 | 89.61 | 0.857 | 83.26 | 88.15 | 0.891 |
MultiEA-Rel | 71.34 | 80.93 | 0.746 | 72.65 | 79.86 | 0.724 | 71.19 | 81.42 | 0.753 |
MultiEA-Attr | 72.50 | 81.72 | 0.793 | 72.37 | 83.64 | 0.801 | 71.92 | 82.96 | 0.785 |
MultiEA-Name-Rel | 85.62 | 90.61 | 0.904 | 86.97 | 91.72 | 0.916 | 86.03 | 91.49 | 0.923 |
MultiEA-Name-Attr | 88.15 | 93.76 | 0.917 | 88.86 | 94.55 | 0.928 | 89.31 | 95.73 | 0.945 |
MultiEA | 90.68 | 97.43 | 0.935 | 93.76 | 97.83 | 0.951 | 96.46 | 98.73 | 0.972 |
表3 DBP15K子数据集上的消融实验结果比较
Tab. 3 Comparison of ablation experimental results on DBP15K sub-datasets
模型 | |||||||||
---|---|---|---|---|---|---|---|---|---|
Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | Hits@1 | Hits@10 | MRR | |
MultiEA-Name | 82.80 | 88.41 | 0.869 | 81.83 | 89.61 | 0.857 | 83.26 | 88.15 | 0.891 |
MultiEA-Rel | 71.34 | 80.93 | 0.746 | 72.65 | 79.86 | 0.724 | 71.19 | 81.42 | 0.753 |
MultiEA-Attr | 72.50 | 81.72 | 0.793 | 72.37 | 83.64 | 0.801 | 71.92 | 82.96 | 0.785 |
MultiEA-Name-Rel | 85.62 | 90.61 | 0.904 | 86.97 | 91.72 | 0.916 | 86.03 | 91.49 | 0.923 |
MultiEA-Name-Attr | 88.15 | 93.76 | 0.917 | 88.86 | 94.55 | 0.928 | 89.31 | 95.73 | 0.945 |
MultiEA | 90.68 | 97.43 | 0.935 | 93.76 | 97.83 | 0.951 | 96.46 | 98.73 | 0.972 |
对齐实体 | 实体名称 辅助对齐 | 实体关系 辅助对齐 | 实体属性 辅助对齐 | MultiEA 辅助对齐 |
---|---|---|---|---|
http://zh.dbpedia.org/resource/汉字 http://dbpedia.org/resource/Chinese | 82.4 | 85.1 | 86.7 | 93.2 |
http://zh.dbpedia.org/resource/美利坚合众国 http://dbpedia.org/resource/USA | 70.3 | 84.2 | 84.9 | 94.6 |
http://dbpedia.org/resource/China http://fr.dbpedia.org/resource/Chine | 93.6 | 94.2 | 94.7 | 95.1 |
http://dbpedia.org/resource/Vampire Detective http://fr.dbpedia.org/resource/Détective vampire | 89.2 | 91.1 | 91.6 | 94.8 |
http://ja.dbpedia.org/resource/風の谷のナウシカ http://dbpedia.org/resource/Nausicaä of the Valley of the Wind (film) | 71.6 | 92.3 | 93.1 | 96.5 |
http://ja.dbpedia.org/resource/眠れる森の美女 (1959 film) http://dbpedia.org/resource/Sleeping Beauty(1959年の映画) | 90.3 | 94.1 | 95.7 | 97.3 |
表4 不同实体在DBP15K子数据集上的Hits@1结果比较 (%)
Tab. 4 Hits@1 results comparison of different entities in DBP15K sub-datasets
对齐实体 | 实体名称 辅助对齐 | 实体关系 辅助对齐 | 实体属性 辅助对齐 | MultiEA 辅助对齐 |
---|---|---|---|---|
http://zh.dbpedia.org/resource/汉字 http://dbpedia.org/resource/Chinese | 82.4 | 85.1 | 86.7 | 93.2 |
http://zh.dbpedia.org/resource/美利坚合众国 http://dbpedia.org/resource/USA | 70.3 | 84.2 | 84.9 | 94.6 |
http://dbpedia.org/resource/China http://fr.dbpedia.org/resource/Chine | 93.6 | 94.2 | 94.7 | 95.1 |
http://dbpedia.org/resource/Vampire Detective http://fr.dbpedia.org/resource/Détective vampire | 89.2 | 91.1 | 91.6 | 94.8 |
http://ja.dbpedia.org/resource/風の谷のナウシカ http://dbpedia.org/resource/Nausicaä of the Valley of the Wind (film) | 71.6 | 92.3 | 93.1 | 96.5 |
http://ja.dbpedia.org/resource/眠れる森の美女 (1959 film) http://dbpedia.org/resource/Sleeping Beauty(1959年の映画) | 90.3 | 94.1 | 95.7 | 97.3 |
1 | ZHANG R, TRISEDYA B D, LI M, et al. A benchmark and comprehensive survey on knowledge graph entity alignment via representation learning[J]. The VLDB Journal, 2022, 31(5): 1143-1168. |
2 | ZHAO X, JIA Y, LI A, et al. Multi-source knowledge fusion: a survey [J]. World Wide Web, 2020, 23: 2567-2592. |
3 | 张富,杨琳艳,李健伟,等. 实体对齐研究综述[J]. 计算机学报, 2022, 45(6): 1195-1225. |
ZHANG F, YANG L Y, LI J W, et al. An overview of entity alignment methods[J]. Chinese Journal of Computers, 2022, 45(6): 1195-1225. | |
4 | COHEN W W, RICHMAN J. Learning to match and cluster large high-dimensional data sets for data integration[C]// Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2002: 475-480. |
5 | HALPIN H, HAYES P J, MCCUSKER J P, et al. When owl: sameAs isn’t the same: an analysis of identity in linked data[C]// Proceedings of the 2010 International Semantic Web Conference, LNCS 6496 . Berlin: Springer, 2010: 305-320. |
6 | 杜雪盈,刘名威,沈立炜,等. 面向链接预测的知识图谱表示学习方法综述[J]. 软件学报, 2024, 35(1): 87-117. |
DU X Y, LIU M W, SHEN L W, et al. Survey on representation learning methods of knowledge graph for link prediction[J]. Journal of Software, 2024, 35(1): 87-117. | |
7 | JIANG J, LI M, GU Z. A survey on translating embedding based entity alignment in knowledge graphs [C]// Proceedings of the IEEE 6th International Conference on Data Science in Cyberspace. Piscataway: IEEE, 2021: 187-194. |
8 | CHEN M, TIAN Y, YANG M, et al. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment [C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2017: 1511-1517. |
9 | BORDES A, USUNIER N, GARCIA-DURÁN A, et al. Translating embeddings for modeling multi-relational data [C]// Proceedings of the 27th International Conference on Neural Information Processing Systems — Volume 2. Red Hook: Curran Associates Inc., 2013: 2787-2795. |
10 | ZHU H, XIE R, LIU Z, et al. Iterative entity alignment via joint knowledge embeddings [C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2017: 4258-4264. |
11 | LIN Y, LIU Z, LUAN H, et al. Modeling relation paths for representation learning of knowledge bases [C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2015: 705-714. |
12 | SUN Z, HU W, LI C. Cross-lingual entity alignment via joint attribute-preserving embedding[C]// Proceedings of the 2017 International Semantic Web Conference, LNCS 10587. Cham: Springer, 2017: 628-644. |
13 | SUN Z, HU W, ZHANG Q, et al. Bootstrapping entity alignment with knowledge graph embedding[C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2018: 4396-4402. |
14 | WANG Z, LV Q, LAN X, et al. Cross-lingual knowledge graph alignment via graph convolutional networks[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018, 349-357. |
15 | ZHOU J, CUI G, HU S, et al. Graph neural networks: a review of methods and applications [J]. AI Open, 2020, 1: 57-81. |
16 | CAO Y, LIU Z, LI C, et al. Multi-channel graph neural network for entity alignment [C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2019, 1452-1461. |
17 | WU Y, LIU X, FENG Y, et al. Relation-aware entity alignment for heterogeneous knowledge graphs[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 5278-5284. |
18 | TRISEDYA B D, QI J, ZHANG R. Entity alignment between knowledge graphs using attribute embeddings [C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 297-304. |
19 | ZHANG Q, SUN Z, HU W, et al. Multi-view knowledge graph embedding for entity alignment[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 5429-5435. |
20 | WANG Z, YANG J, YE X. Knowledge graph alignment with entity-pair embedding [C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 1672-1680. |
21 | GAO S. HyperEA: hyperbolic entity alignment between knowledge graphs[C]// Proceedings of the 4th International Conference on Artificial Intelligence and Big Data. Piscataway: IEEE, 2021: 550-554. |
22 | SUN Z, HU W, WANG C, et al. Revisiting embedding-based entity alignment: a robust and adaptive method[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(8): 8461-8475. |
23 | ZHANG Y, WU J, YU K, et al. Independent relation representation with line graph for cross-lingual entity alignment[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(11): 11503-11514. |
24 | ZHANG X, ZHANG R, CHEN J, et al. Semi-supervised entity alignment with global alignment and local information aggregation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 10464-10477. |
25 | WU Y, LIU X, FENG Y, et al. Neighborhood matching network for entity alignment [C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 6477-6487. |
26 | 苏哲晗,徐涛,戴玉刚,等. 基于属性权重更新网络的跨语言实体对齐方法[J]. 西北工业大学学报, 2024, 42(1):157-164. |
SU Z H, XU T, DAI Y G, et al. Cross-lingual entity alignment method based on attribute weight updating network [J]. Journal of Northwestern Polytechnical University, 2024, 42(1):157-164. |
[1] | 李慧, 贾炳志, 王晨曦, 董子宇, 李纪龙, 仲兆满, 陈艳艳. 基于Swin Transformer的生成对抗网络水下图像增强模型[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1439-1446. |
[2] | 陈满, 杨小军, 杨慧敏. 基于图卷积网络和终点诱导的行人轨迹预测[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1480-1487. |
[3] | 陈路, 王怀瑶, 刘京阳, 闫涛, 陈斌. 融合空间-傅里叶域信息的机器人低光环境抓取检测[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1686-1693. |
[4] | 张庆, 杨凡, 方宇涵. 基于多模态信息融合的中文拼写纠错算法[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1528-1534. |
[5] | 王丹, 张文豪, 彭丽娟. 基于深度学习的智能反射面辅助通信系统信道估计[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1613-1618. |
[6] | 徐春, 吉双焱, 马欢, 孙恩威, 王萌萌, 苏明钰. 基于知识图谱和对话结构的问诊推荐方法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1157-1168. |
[7] | 张李伟, 梁泉, 胡禹涛, 朱乔乐. 基于分组卷积的通道重洗注意力机制[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1069-1076. |
[8] | 姜坤元, 李小霞, 王利, 曹耀丹, 张晓强, 丁楠, 周颖玥. 引入解耦残差自注意力的边界交叉监督语义分割网络[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1120-1129. |
[9] | 胡婕, 郑启扬, 孙军, 张龑. 基于多标签关系图和局部动态重构学习的多标签分类模型[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1104-1112. |
[10] | 王利琴, 耿智雷, 李英双, 董永峰, 边萌. 基于路径和增强三元组文本的开放世界知识推理模型[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1177-1183. |
[11] | 杨定木, 倪龙强, 梁晶, 邱照原, 张永真, 齐志强. 基于语义相似度的协议转换方法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1263-1270. |
[12] | 郭诗月, 党建武, 王阳萍, 雍玖. 结合注意力机制和多尺度特征融合的三维手部姿态估计[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1293-1299. |
[13] | 耿海军, 董赟, 胡治国, 池浩田, 杨静, 尹霞. 基于Attention-1DCNN-CE的加密流量分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 872-882. |
[14] | 蔡启健, 谭伟. 语义图增强的多模态推荐算法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 421-427. |
[15] | 李严, 叶冠华, 李雅文, 梁美玉. 基于丰度协调技术的企业ESG指标预测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 670-676. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||