%0 Journal Article %1 Obraczka2021-ja %A Obraczka, Daniel %A Schuchart, Jonathan %A Rahm, Erhard %D 2021 %I arXiv %K %T EAGER: Embedding-assisted entity Resolution for knowledge graphs %X Entity Resolution (ER) is a constitutional part for integrating different knowledge graphs in order to identify entities referring to the same real-world object. A promising approach is the use of graph embeddings for ER in order to determine the similarity of entities based on the similarity of their graph neighborhood. The similarity computations for such embeddings translates to calculating the distance between them in the embedding space which is comparatively simple. However, previous work has shown that the use of graph embeddings alone is not sufficient to achieve high ER quality. We therefore propose a more comprehensive ER approach for knowledge graphs called EAGER (Embedding-Assisted Knowledge Graph Entity Resolution) to flexibly utilize both the similarity of graph embeddings and attribute values within a supervised machine learning approach. We evaluate our approach on 23 benchmark datasets with differently sized and structured knowledge graphs and use hypothesis tests to ensure statistical significance of our results. Furthermore we compare our approach with state-of-the-art ER solutions, where our approach yields competitive results for table-oriented ER problems and shallow knowledge graphs but much better results for deeper knowledge graphs.

@article{Obraczka2021-ja, abstract = {Entity Resolution (ER) is a constitutional part for integrating different knowledge graphs in order to identify entities referring to the same real-world object. A promising approach is the use of graph embeddings for ER in order to determine the similarity of entities based on the similarity of their graph neighborhood. The similarity computations for such embeddings translates to calculating the distance between them in the embedding space which is comparatively simple. However, previous work has shown that the use of graph embeddings alone is not sufficient to achieve high ER quality. We therefore propose a more comprehensive ER approach for knowledge graphs called EAGER (Embedding-Assisted Knowledge Graph Entity Resolution) to flexibly utilize both the similarity of graph embeddings and attribute values within a supervised machine learning approach. We evaluate our approach on 23 benchmark datasets with differently sized and structured knowledge graphs and use hypothesis tests to ensure statistical significance of our results. Furthermore we compare our approach with state-of-the-art ER solutions, where our approach yields competitive results for table-oriented ER problems and shallow knowledge graphs but much better results for deeper knowledge graphs.}, added-at = {2024-09-10T12:10:36.000+0200}, author = {Obraczka, Daniel and Schuchart, Jonathan and Rahm, Erhard}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/260af7adf609170650cd994e66c35def9/scadsfct}, interhash = {b76656faf37296786e342a5a4dd56f67}, intrahash = {60af7adf609170650cd994e66c35def9}, keywords = {}, publisher = {arXiv}, timestamp = {2024-09-10T15:15:57.000+0200}, title = {{EAGER}: Embedding-assisted entity Resolution for knowledge graphs}, year = 2021 }