Graph Representation Learning

Abstract

Graph structure, which can represent objects and their relationships, is ubiquitous in big data including natural languages. Besides original text as a sequence of word tokens, massive additional information in NLP is in the graph structure, such as syntactic relations between words in a sentence, hyperlink relations between documents, and semantic relations between entities. Hence, it is critical for NLP to encode these graph data with graph representation learning. Graph representation learning, also known as network embedding, has been exten-sively studied in AI and data mining. In this chapter, we introduce a variety of graph representation learning methods that embed graph data into vectors with shallow or deep neural models. After that, we introduce how graph representation learning helps NLP tasks.