Written text usually consists of multiple sentences; to fully understand a text as a whole requires information that cannot be obtained when considering each sentence individually. In this seminar course, we look at discourse processing: how references to entities, and relationships between clauses and sentences (e.g., cause, result, elaboration), contribute to the local coherence of the text. We will study the following aspects: frameworks, corpora, and computational models (e.g., coreference resolution and discourse parsing). We will also discuss discourse processing in the context of a number of Natural Language Processing tasks, such as summarization, question answering, and sentiment analysis.
Graduate standing. LIN 353C or CS 388 or CS 395T or equivalent prior exposure to Computational Linguistics/Natural Language Processing.