Introduction to Computational Models of Discourse

To build systems that truly understand human language, you must look beyond individual sentences to analyze how entire texts and conversations hang together. This text-based course introduces the core computational models used to process, segment, and interpret discourse in modern natural language processing. You will transition from analyzing simple syntax to understanding complex dialogue flows and document structures. By working through this comprehensive guide, you will gain a strong theoretical and practical foundation in discourse analysis, enabling you to build smarter dialogue systems, summarizers, and conversational agents. You will explore both traditional symbolic rules and modern machine learning approaches, including how contemporary large language models handle context and coherence. What you'll learn: - Understand the core concepts of discourse structure, coherence, and cohesion - Implement text segmentation algorithms to divide long documents into topical sections - Apply plan recognition algorithms to model speaker intent in dialogue systems - Analyze symbolic and machine learning methods for automatic discourse processing - Explore modern context-handling techniques, including vector embeddings and attention mechanisms - Evaluate discourse models in practical applications like conversational AI and text summarization This course begins with foundational linguistic definitions and essential terminology before guiding you step-by-step through computational algorithms, core segmentation techniques, and modern machine learning implementations. It is designed for software developers, data scientists, and computational linguistics enthusiasts who want to master text analysis beyond the sentence level. No prior background in advanced discourse theory is required. Start reading today to unlock the deeper structure of human language.