DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs
This addresses the problem of knowledge fusion and integration for researchers and practitioners, representing an incremental improvement over prior methods.
The paper tackles entity alignment in knowledge graphs by proposing a dense entity retrieval framework that uniformly encodes entity features using language models, achieving state-of-the-art performance on cross-lingual and monolingual datasets.
Entity Alignment (EA) aims to match equivalent entities in different Knowledge Graphs (KGs), which is essential for knowledge fusion and integration. Recently, embedding-based EA has attracted significant attention and many approaches have been proposed. Early approaches primarily focus on learning entity embeddings from the structural features of KGs, defined by relation triples. Later methods incorporated entities' names and attributes as auxiliary information to enhance embeddings for EA. However, these approaches often used different techniques to encode structural and attribute information, limiting their interaction and mutual enhancement. In this work, we propose a dense entity retrieval framework for EA, leveraging language models to uniformly encode various features of entities and facilitate nearest entity search across KGs. Alignment candidates are first generated through entity retrieval, which are subsequently reranked to determine the final alignments. We conduct comprehensive experiments on both cross-lingual and monolingual EA datasets, demonstrating that our approach achieves state-of-the-art performance compared to existing EA methods.