Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding

Abstract

Entity alignment is the task of finding entities in two knowledge bases (KBs) that represent the same real-world object. When facing KBs in different natural languages, conventional cross-lingual entity alignment methods rely on machine translation to eliminate the language barriers. These approaches often suffer from the uneven quality of translations between languages. While recent embedding-based techniques encode entities and relationships in KBs and do not need machine translation for cross-lingual entity alignment, a significant number of attributes remain largely unexplored. In this paper, we propose a joint attribute-preserving embedding model for cross-lingual entity alignment. It jointly embeds the structures of two KBs into a unified vector space and further refines it by leveraging attribute correlations in the KBs. Our experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.

References in corpus (3)

• Distributed Representations of Words and Phrases and their Compositionality
• Type-Constrained Representation Learning in Knowledge Graphs
• Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors

Cited by in corpus (8)

• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
• Recurrent Skipping Networks for Entity Alignment
• A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
• A Self-supervised Method for Entity Alignment
• Mitigating Modality Bias in Multi-modal Entity Alignment from a Causal Perspective
• JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment
• Principled Representation Learning for Entity Alignment