Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment
This work addresses the challenge of accurately aligning entities across knowledge graphs, particularly in cross-lingual and monolingual contexts, by mitigating name-bias and leveraging underutilized attribute data.
The paper tackles the problem of entity alignment in knowledge graphs by proposing a method that models attribute triples and partitions graphs, achieving a 5.10% average improvement in Hits@1 over baselines under regular and hard experimental settings.
Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performances by modeling the KG structure defined by relation triples. However, attribute triples can also provide crucial alignment signal but have not been well explored yet. In this paper, we propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently. Besides, the performances of current EA methods are overestimated because of the name-bias of existing EA datasets. To make an objective evaluation, we propose a hard experimental setting where we select equivalent entity pairs with very different names as the test set. Under both the regular and hard settings, our method achieves significant improvements ($5.10\%$ on average Hits@$1$ in DBP$15$k) over $12$ baselines in cross-lingual and monolingual datasets. Ablation studies on different subgraphs and a case study about attribute types further demonstrate the effectiveness of our method. Source code and data can be found at https://github.com/thunlp/explore-and-evaluate.