Computational Linguistics 1
Spring 2007 | Instructors: Jason Baldridge, Katrin Erk | Tuesday and Thursday, 11am-12:30pm | UTC 3.120
Advances in computational linguistics have not only led to industrial applications of language technology; they can also provide useful tools for linguistic investigations of large online collections of text and speech, or for the validation of linguistic theories.
Computational Linguistics I introduces the most important representations and algorithmic techniques used in classical, symbolic computational linguistics: regular expressions and finite-state methods, context-free grammars and parsing, feature structures and unification. The linguistic levels covered are phonology, morphology, syntax (and some semantics). A high-level overview of statistical techniques in computational linguistics will also be given. We will apply the techniques in actual programming exercises, using the programming language Python and the Natural Language Toolkit (http://nltk.sf.net).
The sequel to this course, Computational Linguistics II, addresses empirical methods (primarily statistical) and applications of natural language processing.