SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

Abstract

Knowledge representation is an important, long-history topic in AI, and there have been a large amount of work for knowledge graph embedding which projects symbolic entities and relations into low-dimensional, real-valued vector space. However, most embedding methods merely concentrate on data fitting and ignore the explicit semantic expression, leading to uninterpretable representations. Thus, traditional embedding methods have limited potentials for many applications such as question answering, and entity classification. To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments justify our model outperforms other state-of-the-art baselines substantially.

Submitted to AAAI.2017

Cited by in corpus (32)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• KG-BERT: BERT for Knowledge Graph Completion
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• On Event-Driven Knowledge Graph Completion in Digital Factories
• Knowledge Graph Embedding with Iterative Guidance from Soft Rules
• Knowledge Representation Learning: A Quantitative Review
• From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules
• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
• Augmenting Neural Machine Translation with Knowledge Graphs
• DOLORES: Deep Contextualized Knowledge Graph Embeddings
• A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
• On the Role of Conceptualization in Commonsense Knowledge Graph Construction
• Joint Embedding Learning of Educational Knowledge Graphs
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• Semantic Entity Enrichment by Leveraging Multilingual Descriptions for Link Prediction
• KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm
• Knowledge-Based Distant Regularization in Learning Probabilistic Models
• EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
• Learning Conceptual-Contextual Embeddings for Medical Text
• Type-augmented Relation Prediction in Knowledge Graphs
• SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement
• Medical Knowledge Embedding Based on Recursive Neural Network for Multi-Disease Diagnosis
• Augmenting and Tuning Knowledge Graph Embeddings
• DSKG: A Deep Sequential Model for Knowledge Graph Completion
• The KEEN Universe: An Ecosystem for Knowledge Graph Embeddings with a Focus on Reproducibility and Transferability
• Domain Representation for Knowledge Graph Embedding
• Delving Into Deep Walkers: A Convergence Analysis of Random-Walk-Based Vertex Embeddings
• Can x2vec Save Lives? Integrating Graph and Language Embeddings for Automatic Mental Health Classification
• Automated Feature-Topic Pairing: Aligning Semantic and Embedding Spaces in Spatial Representation Learning
• CNN-based Dual-Chain Models for Knowledge Graph Learning