What Will I Learn
This course covers modern empirical methods in natural language processing. It is designed for language technologies students who want to more deeply understand statistical methodology in the language domain, and for machine learning students who want to know about current problems and solutions in text processing. Students will, upon completion, understand how statistical modeling and learning can be applied to linguistic analysis of text, be able to develop and apply new statistical models to problems in their own research, and be able to critically read papers from the major related conferences. A recurring theme will be the tradeoffs between computational cost, mathematical elegance, expressive power, and applicability to real problems. The course is organized around methods, with concrete examples introduced throughout.