Entity Alignment between Knowledge Graphs Using Attribute Embeddings

By Bayu Distiawan Trisedya, Jianzhong Qi, Rui Zhang. AAAI Conference on Artificial Intelligence, 2019

332 citations recorded by the source corpus.

The task of entity alignment between knowledge graphs aims to find entities in two knowledge graphs that represent the same real-world entity. Recently, embedding-based models are proposed for this task. Such models are built on top of a knowledge graph embedding model that learns entity embeddings to capture the semantic similarity between entities in the same knowledge graph. We propose to learn embeddings that can capture the similarity between entities in different knowledge graphs. Our proposed model helps align entities from different knowledge graphs, and hence enables the integration of multiple knowledge graphs. Our model exploits large numbers of attribute triples existing in the knowledge graphs and generates attribute character embeddings. The attribute character embedding shifts the entity embeddings from two knowledge graphs into the same space by computing the similarity between entities based on their attributes. We use a transitivity rule to further enrich the number of attributes of an entity to enhance the attribute character embedding. Experiments using real-world knowledge bases show that our proposed model achieves consistent improvements over the baseline models by over 50% in terms of hits@1 on the entity alignment task.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/56936d1f4d8c455b4e136a057d18957b912fb79b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Shirui Pan
3. Erik Cambria
4. Wei Hu
5. Zequn Sun
6. Peng Shi
7. Shaoxiong Ji
8. Muhao Chen

In Management Science and Operations Research

1. Wei Hu
2. Zequn Sun
3. Philip S. Yu
4. Shirui Pan
5. Erik Cambria
6. Pekka Marttinen
7. Shaoxiong Ji
8. Xu Sun

Citations in the corpus

• Knowledge Graph Embedding for Link Prediction (2020, neutral): “[64] uses textual or numeric attributes of entities to learn attribute character embeddings, and uses them”
• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, neutral): “y embedding-based systems participating in this track. The preferred evaluation metrics are precision, recall and F1-score. 2.1.3 Embedding-based Entity Alignment Approaches. Many existing approaches [10, 47, 57, 58, 72, 73, 77, 93] employ the translational models (e.g., TransE [5]) to learn entity ”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “learning multiple views of the entity name, relation, and attributes, and alignment with character attribute embedding [118].”
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation (2019, methodology): “On top of KG structures, some work like KDCoE (Chen et al. 2018), AttrE (Trisedya, Qi, and Zhang 2019) and MultiKE (Zhang et al. 2019), incorporates additional profile information of entities such as textual descriptions and literal names for KG embedding.”
• Aligning Cross-Lingual Entities with Multi-Aspect Information (2019, methodology): “As for monolingual entity alignment, main approaches align two entities by computing string similarity of entity labels (Scharffe et al., 2009; Volz et al., 2009; Ngomo and Auer, 2011) or graph similarity (Raimond et al., 2008; Pershina et al., 2015; Azmy et al., 2019).”