Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks

Abstract

Multilingual knowledge graphs (KGs) such as DBpedia and YAGO contain structured knowledge of entities in several distinct languages, and they are useful resources for cross-lingual AI and NLP applications. Cross-lingual KG alignment is the task of matching entities with their counterparts in different languages, which is an important way to enrich the crosslingual links in multilingual KGs. In this paper, we propose a novel approach for crosslingual KG alignment via graph convolutional networks (GCNs). Given a set of pre-aligned entities, our approach trains GCNs to embed entities of each language into a unified vector space. Entity alignments are discovered based on the distances between entities in the embedding space. Embeddings can be learned from both the structural and attribute information of entities, and the results of structure embedding and attribute embedding are combined to get accurate alignments. In the experiments on aligning real multilingual KGs, our approach gets the best performance compared with other embedding-based KG alignment approaches.

Aligning Cross-Lingual Entities with Multi-Aspect Information

“…Such methods only make use of one or two aspects of the aforementioned information. For example, Zhu et al (2017) relied only on topological features while and Wang et al (2018) exploited both topological and attribute features. Chen et al (2018) proposed a co-training algorithm to combine topological features and literal descriptions of entities.…”

“…Graph convolutional networks (GCNs) (Kipf and Welling, 2017) are variants of convolutional networks that have proven effective in capturing information from graph structures, such as dependency graphs (Guo et al, 2019b), abstract meaning representation graphs (Guo et al, 2019a), and knowledge graphs (Wang et al, 2018). In practice, multi-layer GCNs are stacked to collect evidence from multi-hop neighbors.…”

Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned

“…Convolution Weights The first column of Table 5 corresponds to the weight usage and initialization settings used in the code for GCN-Align. We achieve slightly better results than published in [24], which we attribute to a more exhaustive parameter search. Interestingly, all best configurations use Adam optimizer instead of SGD.…”

“…MTransE [5] WK3l-15K, WK3l-120K, CN3l H@10(, MR) yes IPTransE [29] DFB-{1,2,3} H@{1,10}, MR yes JAPE [19] DBP15K(JAPE) H@{1,10,50}, MR yes KDCoE [4] WK3l-60K H@{1,10}, MR yes BootEA [20] DBP15K(JAPE), DWY100K H@{1,10}, MRR yes SEA [15] WK3l-15K, WK3l-120K H@{1,5,10}, MRR yes MultiKE [28] DWY100K H@{1,10}, MR, MRR yes AttrE [22] DBP-LGD,DBP-GEO,DBP-YAGO H@{1,10}, MR yes RSN [8] custom DBP15K, DWY100K H@{1,10}, MRR yes GCN-Align [24] DBP15K(JAPE) H@{1,10,50} yes CL-GNN [27] DBP15K(JAPE) H@{1,10} yes MuGNN [3] DBP15K(JAPE), DWY100K H@{1,10}, MRR yes NAEA [30] DBP15K(JAPE), DWY100K H@{1,10}, MRR no…”

“…Doing so, we obtain the number of alignments given in brackets. statistics of the larger dataset, and does not mention the reduction of the dataset, subsequent papers also report the statistics of the larger dataset, although experiments use the smaller variant [19,21,24,3,29].…”