This textbook is organized as follows:

Chapter 1 provides an overview of natural language processing from the perspective of graph theory. Chapter 2 introduces traditional graph-based methods. Chapter 3 delves into graph neural networks. Chapter 4 explains graph construction. Chapter 5 discusses graph representation learning. Chapter 6 covers graph encoder-decoder models. Chapter 7 explores applications of graph neural networks in natural language processing. Chapter 8 discusses the challenges of using graph neural networks in natural language processing. Finally, Chapter 9 looks at the future directions for graph neural networks in natural language processing.

Figure 1 systematically categorizes approaches to graph neural networks in natural language processing along four axes: graph construction, graph representation learning, encoder-decoder models, and applications.