L645 Advanced Natural Language Processing
3 Credits

In recent years, statistical methods have become the standard in the
field of Natural Language Processing (NLP).  This course gives an
introduction to statistical models and machine learning paradigms in
NLP.  Such methods are helpful for the following goals: reaching
wide coverage, reducing ambiguity, automatic learning, increasing
robustness, etc.

In this course, we will cover basic notions in statistics, focused
on the concepts needed for NLP. Then we will discuss (Hidden) Markov
Models, exemplified by an approach to POS tagging.  The following
sessions will be dedicated to probabilistic approaches to parsing.
Here, we will start with an introduction to parsing in general, and
then focus on probabilistic context-free grammars. In the last part
of the course, we will cover statistical alignment methods and their
use in statistical machine translation.

We will work with the following textbook:

Christopher Manning, Hinrich SchŸtze (1999) Foundations of
Statistical Natural Language Processing. MIT Press.