EventEA: Benchmarking Entity Alignment for Event-centric Knowledge Graphs

TL;DR

This paper critically evaluates existing embedding-based entity alignment methods for event-centric knowledge graphs, revealing their limitations and introducing a new dataset and a time-aware literal encoder to improve performance.

Contribution

It identifies biases in current datasets, creates a more challenging heterogeneous dataset, and proposes a novel time-aware literal encoder for better entity alignment.

Findings

Existing methods perform poorly on the new dataset.

Biases in previous datasets favor certain techniques.

The proposed encoder shows improved results.

Abstract

Entity alignment is to find identical entities in different knowledge graphs (KGs) that refer to the same real-world object. Embedding-based entity alignment techniques have been drawing a lot of attention recently because they can help solve the issue of symbolic heterogeneity in different KGs. However, in this paper, we show that the progress made in the past was due to biased and unchallenging evaluation. We highlight two major flaws in existing datasets that favor embedding-based entity alignment techniques, i.e., the isomorphic graph structures in relation triples and the weak heterogeneity in attribute triples. Towards a critical evaluation of embedding-based entity alignment methods, we construct a new dataset with heterogeneous relations and attributes based on event-centric KGs. We conduct extensive experiments to evaluate existing popular methods, and find that they fail to achieve promising performance. As a new approach to this difficult problem, we propose a time-aware literal encoder for entity alignment. The dataset and source code are publicly available to foster future research. Our work calls for more effective and practical embedding-based solutions to entity alignment.