A Short Survey on Deep Learning-Based Frameworks for Knowledge Graph Applications

Knowledge Graphs (KG) are repositories of structured, machine-readable data stored as relational triples. DBpedia, Freebase, and YAGO are examples of KGs that have been playing a vital role in many applications, including question answering systems, recommendation systems, and expert systems. Deep learning is a subset of machine learning techniques that consists of layers of artificial neural networks. It is a relatively young technology that, in a very short amount of time, has achieved state-of-the-art performance in many fields of science, business, and government. For instance, convolutional networks have achieved major breakthroughs in processing image, video, and audio files. Moreover, recurrent networks have a similar effect in processing sequential data, such as texts and time series [1]. In this survey, we shed light on the development deep learning has brought about in two KG tasks: entity summarization and entity linking. Experiments on standard performance measures and benchmark datasets show that deep learning-based models generally outperform other models by a considerable margin.