Text data in digital format (e.g., physician’s notes, pathology reports, notes accompanying radiographic images, operational notes, text from digital content) are a commonly underutilized resource in the pharmaceutical industry. Supervised and unsupervised natural language processing techniques have been used in the past to represent medical knowledge and medical evidence generation. However, challenges remain with such techniques, including accuracy, ease of transfer to new text-based datasets, and the capability for integration with other types of structured data (e.g., genomics, structures, targets, vocabularies). Graph-based natural language processing approaches have the potential to address these challenges. With this chapter, we present an overview of graph-based NLP techniques used in the pharmaceutical industry. Borrowing from the strengths of existing approaches outside the pharmaceutical industry, we propose recommendations for graph-based NLP techniques for pharmaceutical industry use cases.