Course: Natural Language Processing

Prof. Jacques Savoy
University of Neuchatel
Computer Science Department

Main objective

The main objective of this course is to introduce the students to the underlying problems when facing with natural languages data.

• Representation and standards;
• Statistical methods for natural language processing;
• Prolog and parsing;
• Markov Models

Practical exercises will complete the theoretical presentation.

Description

Introduction to Perl and XML; Introduction to linguistics (morphology, syntax, semantics); simple statistical approaches (KWIC, concordances); automata and natural language (FSTN, RTN, ATN); Spelling detection and correction; Statistical models (counting words, bigramns, entropy); Markov chains; Hidden Markov chains; Information retrieval.

The final mark is based on both a final written exam and the results of the practical exercices.

References

• Christopher D. Manning, Hinrich Schütze: Foundations of Statistical Natural Language Processing. The MIT Press, Cambridge (MA).
• Gerald Gazdar, Chris Mellish: Natural Language Processing in Prolog. An Introduction to Computational Linguistics. Addison-Wesley, Workingham (UK).
• Pierre Nugues: An Introduction to Language Processing with Perl and Prolog. Springer, Berlin, 2006.

Other references
• Eugene Charniak: Statistical Language Learning. The MIT Press, Cambridge (MA).
• Ian H. Witten, David Bainbridge: How to Build a Digital Library. Morgan Kaufmann, 2003.
• Maxime Crochemore, Christophe Hancart, Thierry Lecrocq: Algorithms on Strings. Cambridge University Press (UK), 2007.

Additional information

• Natural Language on the Web
• Journal Computational Linguistics
• Examples of aligned corpora at EU (from 21 languages)
• Sur les sentiers de la linguistique
• Help on statistical methods (from the NIST)
• The Web and linguistics
• The WordNet lexical database
• The EuroWordNet project
• Un lexique (in French)
• Le portail technolangue
• About Chomsky
• Overview of the English grammar
• The GNU aspell spell checker
• The W3C Consortium
• An online XML tutorial
• Unicode
• ASCII table and description
• Table UTF-8 Unicode for HTML UTF-8 pages
• Access to the IPA fonts
• How to read spectrogram?
• How Much Information? (Berkeley studies), see also this article in JEP
• How Many Bytes in Human memory?
• How Much Information is There in the World?

Advances NLP tools

• TreeTagger, free POS tagger (English, German, French, Italian)
• Stanford POS tagger
• The MINIPAR syntactical analysis of English language (click here for a demo)
• List of variousparsers
• Online resourcesfor studying English syntax, words and usage

To get a version of Prolog and Corpora

• SWI-Prolog, a free version
• SICStus Prolog, a complete version of Prolog
• OpenProlog, another free version.
• ELRA European language resources association
• Oxford text archive
• LDC Linguistic data consortium

Prof. Jacques Savoy
Universite de Neuchatel
Computer Science Department
Rue Emile-Argand 11
CH-2009 Neuchâtel
Switzerland


+41 32 718 1375 (phone)
+41 32 718 2701 (fax)