This course presents an introduction to methods for intelligently processing human language data in text form, as well as relevant linguistic background. It will include coverage of fundamental topics in natural language processing such as ngram language models, part-of-speeech tagging, parsing, and lexical semantics, as well as applications such as special correction, document classification, information retrieval, and machine translation. Students are expected to implement and evaluate a variety of natural language procesing methods, as well as write reports describing their implementations and their performance. |