Leveraging Lexical Semantic Information for Learning Concept-Based Multiple Embedding Representations for Knowledge Graph Completion

Knowledge graphs (KGs) are important resources for a variety of natural language processing tasks but suffer from incompleteness. To address this challenge, a number of knowledge graph completion (KGC) methods have been developed using low-dimensional graph embeddings. Most existing methods focus on the structured information of triples in encyclopaedia KG and maximize the likelihood of them. However, they neglect semantic information contained in lexical KG. To overcome this drawback, we propose a novel KGC method (named as TransC), that integrates the structured information in encyclopaedia KG and the entity concepts in lexical KG, which describe the categories of entities. Since all entities appearing in the head (or tail) position with the same relation have some common concepts, we introduce a novel semantic similarity to measure the distinction of entity semantics with the concept information. And then TransC utilizes concept-based semantic similarity of the related entities and relations to capture prior distributions of entities and relations. With the concept-based prior distributions, TransC generates multiple embedding representations of each entity in different contexts and estimates the posterior probability of entity and relation prediction. Experimental results demonstrate the efficiency of the proposed method on two benchmark datasets.