Type-Constrained Representation Learning in Knowledge Graphs

Abstract

Large knowledge graphs increasingly add value to various applications that require machines to recognize and understand queries and their semantics, as in search or question answering systems. Latent variable models have increasingly gained attention for the statistical modeling of knowledge graphs, showing promising results in tasks related to knowledge graph completion and cleaning. Besides storing facts about the world, schema-based knowledge graphs are backed by rich semantic descriptions of entities and relation-types that allow machines to understand the notion of things and their semantic relationships. In this work, we study how type-constraints can generally support the statistical modeling with latent variable models. More precisely, we integrated prior knowledge in form of type-constraints in various state of the art latent variable approaches. Our experimental results show that prior knowledge on relation-types significantly improves these models up to 77% in link-prediction tasks. The achieved improvements are especially prominent when a low model complexity is enforced, a crucial requirement when these models are applied to very large datasets. Unfortunately, type-constraints are neither always available nor always complete e.g., they can become fuzzy when entities lack proper typing. We show that in these cases, it can be beneficial to apply a local closed-world assumption that approximates the semantics of relation-types based on observations made in the data.

Cited by in corpus (20)

• PyTorch-BigGraph: A Large-scale Graph Embedding System
• Neighborhood Mixture Model for Knowledge Base Completion
• KBGAN: Adversarial Learning for Knowledge Graph Embeddings
• Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
• Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence
• Learning with Memory Embeddings
• Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
• Role-Aware Modeling for N-ary Relational Knowledge Bases
• Rule-Guided Compositional Representation Learning on Knowledge Graphs
• AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding
• Compositional Learning of Relation Path Embedding for Knowledge Base Completion
• Out-of-Vocabulary Entities in Link Prediction
• TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
• KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
• Knowledge Graph Alignment using String Edit Distance
• Knowledge Completion for Generics using Guided Tensor Factorization
• Clustering as an Evaluation Protocol for Knowledge Embedding Representation of Categorised Multi-relational Data in the Clinical Domain
• RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
• A Systematic Investigation of KB-Text Embedding Alignment at Scale
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation