A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment

Proceedings of the 28th International Conference on Computational Linguistics, pages 5918–5928 Barcelona, Spain (Online), December 8-13, 2020 5918 A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment Zhiwen Xie1, Runjie Zhu2, Kunsong Zhao1, Jin Liu1∗, Guangyou Zhou3, Jimmy Xiangji Huang4 1School of Computer Science, Wuhan University 2Lassonde School of Engineering, York University 2AI Singapore, Singapore 3School of Computer Science, Central China Normal University 4School of Information Technology, York University {xiezhiwen,kszhao,jinliu}@whu.edu.cn, sherryzh@cse.yorku.ca sherryzhu@aisingapore.org gyzhou@mail.ccnu.edu.cn, jhuang@yorku.ca Abstract Cross-lingual entity alignment, which aims to match equivalent entities in KGs with different lan- guages, has attracted considerable focus in recent years. Recently, many graph neural network (GNN) based methods are proposed for entity alignment and obtain promising results. How- ever, existing GNN-based methods consider the two KGs independently and learn embeddings for different KGs separately, which ignore the useful pre-aligned links between two KGs. In this paper, we propose a novel Contextual Alignment Enhanced Cross Graph Attention Network (CAECGAT) for the task of cross-lingual entity alignment, which is able to jointly learn the em- beddings in different KGs by propagating cross-KG information through pre-aligned seed align- ments. We conduct extensive experiments on three benchmark cross-lingual entity alignment datasets. The experimental results demonstrate that our proposed method obtains remarkable performance gains compared to state-of-the-art methods. 1 Introduction Knowledge graphs (KGs) have recently demonstrated their potential in many natural language processing (NLP) tasks, such as language modelling (Zhang et al., 2019) and question answering (Wu et al., 2019a). With the rapid growth of multilingual KGs, such as DBpedia (Lehmann et al., 2015) and YAGO (Rebele et al., 2016; Suchanek et al., 2008), cross-lingual entity alignment has attracted considerable focus due to the lack of cross-lingual links. The task of cross-lingual entity alignment aims to automatically detect equivalent entities from different monolingual KGs to bridge the language gap. Most recently, many graph neural networks (GNNs) based methods are proposed for entity alignment (Xu et al., 2019; Wang et al., 2018; Mao et al., 2020; Cao et al., 2019; Yang et al., 2019; Sun et al., 2019). Since GNNs are powerful to model graph-structured data by aggregating neighborhood infor- mation, the GNN-based methods have shown promising performance. However, existing GNN-based methods model different KGs separately, which ignore the useful pre-aligned links between two KGs. These GNN-based methods only use the pre-aligned seed alignments to optimize the objective function during training and fail to take full use of seed alignments, which provide useful contextual alignment information for entity alignment task. Intuitively, if two entities in different KGs share many pre-aligned neighbors, they are most likely to be equivalent entities. Taking the example shown in Figure 1(a), al- though the entity “哥威迅语(Gothic language)” in Chinese from G1 has the same translated surface form with the entity “Gothic language” in English from G2, the correct alignment for “哥威迅语(Gothic language)” is the entity “Gwich’in language” in English. By considering the contextual alignments in different KGs, such as “美国(United States)” and “United States”, “加拿大(Canada)” and “Canada”, “纳－德内语系(Na de nene)” and …

Content truncated to 500 words