Filters








6 Hits in 2.2 sec

SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs [article]

Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang
2022 pre-print
The performance of SelfKG suggests that self-supervised learning offers great potential for entity alignment in KGs. The code and data are available at https://github.com/THUDM/SelfKG.  ...  Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing Web-scale KGs.  ...  CONCLUSION In this work, we re-examine the use and effect of supervision in the entity alignment problem, which targets aligning entities with identical meanings across different knowledge graphs.  ... 
doi:10.1145/3485447.3511945 arXiv:2203.01044v1 fatcat:2rjtqyxievamfl7budjafongvy

An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detection [article]

Shengxuan Luo, Sheng Yu
2022 arXiv   pre-print
Knowledge graph integration typically suffers from the widely existing dangling entities that cannot find alignment cross knowledge graphs (KGs).  ...  In this paper, we propose a novel accurate Unsupervised method for joint Entity alignment (EA) and Dangling entity detection (DED), called UED.  ...  Introduction Entity alignment (EA) that aligns the equivalent entities in different knowledge graphs (KGs) is a fundamental technique for knowledge graph integration.  ... 
arXiv:2203.05147v1 fatcat:oesytag7brehtpdd7vq3eqwnvi

State-of-the-Art Instance Matching Methods for Knowledge Graphs

Alex Boyko, Siamak Farshidi, Zhiming Zhao
2021 Zenodo  
A systematic literature review captures knowledge regarding the state-of-the-art systematically, to analyze and report it in the form of reusable knowledge.  ...  After that, it iteratively aligns the entities and relations in a semi-supervised manner.  ...  learning, unsupervised, self-supervised, reinforcement, deep).  ... 
doi:10.5281/zenodo.6547684 fatcat:6awr6ln7yfbb5mpnqx5ehmbase

Machine Learning-Based Semantic Entity Alignment for Multi-Source Data: a Systematic Literature Review

Alex Boyko, Siamak Farshidi, Zhiming Zhao
2021 Zenodo  
Entity alignment helps with merging and managing such data by identifying and linking similar entities stored in each of the data sources.  ...  Many machine learning-based semantic entity alignment approaches have been proposed by the recent studies in the field.  ...  of machine learning approaches are used (supervised learning, unsupervised, self-supervised, reinforcement, deep).  ... 
doi:10.5281/zenodo.6328248 fatcat:kl4julgduffzzhyxztsfxzsw3a

An Accurate Unsupervised Method for Joint Entity Alignment and Dangling Entity Detection

Shengxuan Luo, Sheng Yu
2022 Findings of the Association for Computational Linguistics: ACL 2022   unpublished
Knowledge graph integration typically suffers from the widely existing dangling entities that cannot find alignment cross knowledge graphs (KGs).  ...  In this paper, we propose a novel accurate Unsupervised method for joint Entity alignment (EA) and Dangling entity detection (DED), called UED.  ...  Introduction Entity alignment (EA) that aligns the equivalent entities in different knowledge graphs (KGs) is a fundamental technique for knowledge graph integration.  ... 
doi:10.18653/v1/2022.findings-acl.183 fatcat:of4p24ymcjcqncdshldnlmolbi

ICLEA: Interactive Contrastive Learning for Self-supervised Entity Alignment [article]

Kaisheng Zeng, Zhenhao Dong, Lei Hou, Yixin Cao, Minghao Hu, Jifan Yu, Xin Lv, Juanzi Li, Ling Feng
2022
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments.  ...  ., entity description), and how to effectively leverage those information has not been adequately investigated in self-supervised EA.  ...  Our work significantly narrows the gap between supervised and self-supervised EA approaches 1 . Problem Definition Definition 1 (Knowledge Graph).  ... 
doi:10.48550/arxiv.2201.06225 fatcat:cb2bsujg4renjipx4l7txku7zq