Only open for students of the MA CAI, other students need permission from the programmecoordinator.

As humans we learn our first language from experience. Can machines do the same? Especially, can computers learn linguistic generalizations from written texts? The area of corpus-based natural language processing strives to answer these questions. In this course we will learn a variety of principles and techniques that will allow us to develop working tools for analysis of words, sentences and texts using statistical methods. Selected topics will include: statistical inference and evaluation, Hidden Markov Models for morphological  disambiguation, statistical parsing models, and methods for word. sense disambiguation.