TransG : A Generative Mixture Model for Knowledge Graph Embedding

Abstract

Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence. This paper addresses a new issue of multiple relation semantics that a relation may have multiple meanings revealed by the entity pairs associated with the corresponding triples, and proposes a novel Gaussian mixture model for embedding, TransG. The new model can discover latent semantics for a relation and leverage a mixture of relation component vectors for embedding a fact triple. To the best of our knowledge, this is the first generative model for knowledge graph embedding, which is able to deal with multiple relation semantics. Extensive experiments show that the proposed model achieves substantial improvements against the state-of-the-art baselines.

References in corpus (1)

• Modeling Relation Paths for Representation Learning of Knowledge Bases

Cited by in corpus (11)

• Representation Learning for Natural Language Processing
• Recommender systems based on graph embedding techniques: A comprehensive review
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
• Augmenting Neural Machine Translation with Knowledge Graphs
• Entity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning
• Composing Knowledge Graph Embeddings via Word Embeddings
• Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• A Structural Representation Learning for Multi-relational Networks
• Expeditious Generation of Knowledge Graph Embeddings
• Inducing Interpretability in Knowledge Graph Embeddings