A Joint Embedding Method for Entity Alignment of Knowledge Bases

Multilingual knowledge graphs (KGs), such as YAGO and DBpedia, represent entities in different languages. The task of cross-lingual entity alignment is to match entities in a source language with their counterparts in target languages. In this work, we investigate embedding-based approaches to encode entities from multilingual KGs into the same vector space, where equivalent entities are close to each other. Specifically, we apply graph convolutional networks (GCNs) to combine multiaspect information of entities, including topological connections, relations, and attributes of entities, to learn entity embeddings. To exploit the literal descriptions of entities expressed in different languages, we propose two uses of a pretrained multilingual BERT model to bridge cross-lingual gaps. We further propose two strategies to integrate GCN-based and BERTbased modules to boost performance. Extensive experiments on two benchmark datasets demonstrate that our method significantly outperforms existing systems.

show abstract

“…We first compare MAN and HMAN against previous systems (Hao et al, 2016;Chen et al, 2017a;Wang et al, 2018). As shown in @1 .…”

Section: Results On Graph Embeddingsmentioning

confidence: 99%

“…Hao et al (2016) 21.2 42.7 56.7 19.5 39.3 53.2 18.9 39.9 54.2 17.8 38.4 52.4 15.3 38.8 56.5 14.6 37.2 54.0 Chen et al (2017a) 30.8 61.4 79.1 24.7 52.4 70.4 27.8 57.4 75.9 23.7 49.9 67.9 24.4 55.5 74.4 21.2 50.6 69.9 Sun et al (2017) 41.1 74.4 88.9 40.1 71.0 86.1 36.2 68.5 85.3 38.3 67.2 82.6 32.3 66.6 83.1 32.9 65.9 82.3…”

mentioning

confidence: 99%

Aligning Cross-Lingual Entities with Multi-Aspect Information

Yang

Zou

Shi

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

129

View full text Add to dashboard Cite

show abstract

“…In contrast, JE [11] uses the margin-based ranking loss from TransE [1], while MTransE [5] does not have this as it does not use negative triples. However, as explained in Section 3.2, we argue that negative triples are effective in distinguishing the relations between entities.…”

Section: Discussionmentioning

confidence: 99%

Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding

Sun

2017

Lecture Notes in Computer Science

309

307

View full text Add to dashboard Cite

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.

show abstract

“…The hop size K of GCN 1 and GCN 2 are set to 2 and 3, respectively. The Method ZH-EN EN-ZH JA-EN EN-JA FR-EN EN-FR @1 @10 @1 @10 @1 @10 @1 @10 @1 @10 @1 @10 Hao (2016) 21 non-linearity function σ is ReLU (Glorot et al, 2011) and the parameters of aggregators are randomly initialized. Since KGs are represented in different languages, we first retrieve monolingual fastText embeddings (Bojanowski et al, 2017) for each language, and apply the method proposed in Conneau et al (2017) to align these word embeddings into a same vector space, namely, crosslingual word embeddings.…”

Section: Methodsmentioning

confidence: 99%

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

Wang

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

218

132

View full text Add to dashboard Cite

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs. In this paper, we introduce the topic entity graph, a local sub-graph of an entity, to represent entities with their contextual information in KG. From this view, the KB-alignment task can be formulated as a graph matching problem; and we further propose a graph-attention based solution, which first matches all entities in two topic entity graphs, and then jointly model the local matching information to derive a graphlevel matching vector. Experiments show that our model outperforms previous state-of-theart methods by a large margin.

show abstract

A Joint Embedding Method for Entity Alignment of Knowledge Bases

Cited by 89 publications

References 18 publications

Aligning Cross-Lingual Entities with Multi-Aspect Information

Aligning Cross-Lingual Entities with Multi-Aspect Information

Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

Contact Info

Product

Resources

About