Compositional Vector Space Models for Knowledge Base Completion

Abstract

Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic feature, like bornIn(X,Z) -> containedIn(Z,Y). This paper presents an approach that reasons about conjunctions of multi-hop relations non-atomically, composing the implications of a path using a recursive neural network (RNN) that takes as inputs vector embeddings of the binary relation in the path. Not only does this allow us to generalize to paths unseen at training time, but also, with a single high-capacity RNN, to predict new relation types not seen when the compositional model was trained (zero-shot learning). We assemble a new dataset of over 52M relational triples, and show that our method improves over a traditional classifier by 11%, and a method leveraging pre-trained embeddings by 7%.

The 53rd Annual Meeting of the Association for Computational Linguistics and The 7th International Joint Conference of the Asian Federation of Natural Language Processing, 2015

References in corpus (6)

• Neural Machine Translation by Jointly Learning to Align and Translate
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Grammar as a Foreign Language
• Learning Longer Memory in Recurrent Neural Networks
• Investigating the Role of Prior Disambiguation in Deep-learning Compositional Models of Meaning

Cited by in corpus (35)

• Quaternion Knowledge Graph Embeddings
• End-to-End Differentiable Proving
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
• Traversing Knowledge Graphs in Vector Space
• Modeling Relational Data with Graph Convolutional Networks
• Explainable Reasoning over Knowledge Graphs for Recommendation
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction
• Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs
• Neighborhood Mixture Model for Knowledge Base Completion
• Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs
• Context-aware Path Ranking for Knowledge Base Completion
• Knowledge Graph Embedding with Iterative Guidance from Soft Rules
• Knowledge Representation Learning: A Quantitative Review
• VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering
• Knowledge Graph Representation with Jointly Structural and Textual Encoding
• DOLORES: Deep Contextualized Knowledge Graph Embeddings
• Knowledge Representation via Joint Learning of Sequential Text and Knowledge Graphs
• Reasoning over RDF Knowledge Bases using Deep Learning
• VQA-LOL: Visual Question Answering under the Lens of Logic
• Predicting ConceptNet Path Quality Using Crowdsourced Assessments of Naturalness
• Link Prediction using Embedded Knowledge Graphs
• Rule-Guided Compositional Representation Learning on Knowledge Graphs
• Message Passing Query Embedding
• Group Representation Theory for Knowledge Graph Embedding
• Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs
• Compositional Learning of Relation Path Embedding for Knowledge Base Completion
• Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
• Row-less Universal Schema
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning