Statistical Natural Language Processing
The course introduces basics of statistical natural language processing (NLP) including both linguistics concepts such as morphology and syntax and machine learning techniques relevant for NLP.
NLP is a domain-centered field, as opposed to technique centered fields such as ML, and as such there is no “theory of NLP” which can be taught in a cumulative technique-centered way. Instead this course will focus on different NLP topics and tasks such as machine translation, sequence tagging, constituent and dependency parsing, information extraction, and semantics.
The course will have a strong applied character, which coursework to be programmed, and lab classes that teach students to write software that processes language.