Semantics Driven Multi-View Knowledge Graph Embedding for Cross-Lingual Entity Alignment

Xin Zhang, Yu Liu, Zhehuan Zhao

Abstract: Cross-lingual entity alignment (EA) is a critical step in the integration of multilingual knowledge, which aims to match entities with the same meaning in different knowledge graphs (KGs). Recently, based on GCN models and pre-trained language models (PLMs), EA has achieved breakthrough performance by utilizing graph structures and auxiliary semantic information. However, existing EA methods rely heavily on artificially exploring and designing the interaction of graph structures and auxiliary semantic information, which limits their applicability in real-world situations. In this work, we proposed a simple but effective Semantics Driven Multi-view Knowledge Graph Embedding for cross-lingual entity alignment (SDMKGE). Our proposed SDMKGE utilizes two Siamese Networks based on PLMs to encode the semantics of entities and structures separately, which effectively reduces the difficulty of feature aggregation. We use three well-known datasets to evaluate our SDMKGE. Experimental results demonstrate that our framework outperforms the state-of-the-art EA methods.