Dual Attention Network for Cross-lingual Entity Alignment

Proceedings of the 28th International Conference on Computational Linguistics, pages 3190–3201 Barcelona, Spain (Online), December 8-13, 2020 3190 Dual Attention Network for Cross-lingual Entity Alignment Jian Sun1,2, Yu Zhou 1,2,3 and Chengqing Zong1,2 1 School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, P.R.China 2 National Laboratory of Pattern Recognition, Institute of Automation, CAS 3Beijing Fanyu Technology Co., Ltd, Beijing, China {jian.sun, yzhou, cqzong}@nlpr.ia.ac.cn Abstract Cross-lingual Entity alignment is an essential part of building a knowledge graph, which can help integrate knowledge among different language knowledge graphs. In the real KGs, there exists an imbalance among the information in the same hierarchy of corresponding entities, which re- sults in the heterogeneity of neighborhood structure, making this task challenging. To tackle this problem, we propose a dual attention network for cross-lingual entity alignment (DAEA). Specif- ically, our dual attention consists of relation-aware graph attention and hierarchical attention. The relation-aware graph attention aims at selectively aggregating multi-hierarchy neighborhood in- formation to alleviate the difference of heterogeneity among counterpart entities. The hierarchi- cal attention adaptively aggregates the low-hierarchy and the high-hierarchy information, which is beneficial to balance the neighborhood information of counterpart entities and distinguish non- counterpart entities with similar structures. Finally, we treat cross-lingual entity alignment as a process of linking prediction. Experimental results on three real-world cross-lingual entity align- ment datasets have shown the effectiveness of DAEA. 1 Introduction In recent years, many large-scale knowledge graphs (Bordes et al., 2013; Mahdisoltani et al., 2015; Auer et al., 2007) are built to represent and organize the explosive information over the Internet. They have been widely used in many fields, such as dialogue system (Wang et al., 2019), machine translation (Zhao et al., 2020) and medicine (Yan et al., 2020). However, the KGs are usually incomplete, so it is necessary to manually track emerging concepts and dynamically update the knowledge bases, making the whole process quite expensive. Fortunately, KGs of different languages are often complementary, which means that many components can be shared. To integrate this complementary knowledge, researches begin to pay attention to cross-lingual entity alignment. Cross-lingual entity alignment aims at finding entities with the same semantics in KGs of different lan- guages. Various methods have been explored for cross-lingual entity alignment. Traditional approaches rely on machine translation or feature engineering (Chen et al., 2013; Mahdisoltani et al., 2015; Otani et al., 2018; Feng et al., 2016). The effectiveness of these methods depends largely on the quality of the translation and the nature of the definition. Recently, many embedding approaches based on graph neural network (GNN) are proposed for cross-lingual entity alignment (Wang et al., 2018; Li et al., 2019; Sun et al., 2020; Wu et al., 2019a). These methods first represent the entities and relations in low dimensional spaces and then utilize the powerful encoding ability of graph neural network to learn vector represen- tations for entity or relation. Finally, a mapping function is used to align the entities from the source knowledge graph to the target one. …

Content truncated to 500 words