This is a graduate course focusing on topics in natural language processing such as language models, vector space models, distributional semantics, document classification, part-of-speech tagging, named entity recognition, dependency parsing, coreference resolution, entity linking, semantic parsing, and question answering. This course also covers computational grammars such as context-free grammar, tree-adjoining grammar, combinatory categorial grammar, and head-driven grammar as well as computational lexicons such as PropBank, FrameNet, VerbNet, WordNet, and Abstract Meaning Representations. Advanced topics in machine learning such as adaptive gradient descent, structured prediction, dataset aggregation, neural network models are discussed in applications to NLP.