Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion

Abstract

Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities and relations into the same continuous vector space. In this model, both entity and relation embeddings are learned by taking knowledge graph and plain text into consideration. In experiments, we evaluate the joint learning model on three tasks including entity prediction, relation prediction and relation classification from text. The experiment results show that our model can significantly and consistently improve the performance on the three tasks as compared with other baselines.

References in corpus (4)

• Natural Language Processing (almost) from Scratch
• Relation Classification via Recurrent Neural Network
• Classifying Relations by Ranking with Convolutional Neural Networks
• Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path

Cited by in corpus (10)

• ERNIE: Enhanced Language Representation with Informative Entities
• K-BERT: Enabling Language Representation with Knowledge Graph
• Representation Learning for Natural Language Processing
• KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
• Knowledge Representation Learning: A Quantitative Review
• Knowledge Graph Representation with Jointly Structural and Textual Encoding
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Collaborative Policy Learning for Open Knowledge Graph Reasoning
• Semantically Enhanced Models for Commonsense Knowledge Acquisition
• Is Aligning Embedding Spaces a Challenging Task? A Study on Heterogeneous Embedding Alignment Methods