Computers and Natural Language 1

The course is not on the list Without time-table
Code Completion Credits Range Language
01POPJ1 Z 2 0+2 Czech
Department of Mathematics

Basic course of computational processing and understanding of natural languages. Automatic methods of morphological and syntactic analysis including modern statistical methods of result disambiguation will be discussed. Two-level morphology, tagging and language models, Viterbi algorithm, grammars, chart parsing, probabilistic grammars.

Syllabus of lectures:

1. Introduction, overview of applications. 2. The Perl programming language. 3. Corpora, first applications. 4. Linguistic terminology, layers of natural language processing. 5. Accuracy evaluation. 6. Dictionaries and morphological tags. 7. Two-level morphology, morphonology. 8. Morphology and context-free grammars. 9. Morphology and unification grammars. 10. Tagging (disambiguation of morphological analysis). 11. Spellchecking. 12. Constituency syntax. 13. Dependency syntax.

Syllabus of tutorials:
Study Objective:

Knowledge of basic methods of natural language processing from tokenization to the level of syntactic parsing. Ability to implement some of them in Perl. Ability to work with annotated corpora and existing freely available tools such as taggers and parsers.

Study materials:

Key references:

James Allen: Natural Language Understanding. The Benjamin/Cummings Publishing Company, Inc.; Redwood City, California,1994. ISBN 0-8053-0334-0.

Recommended references:

Larry Wall, Tom Christiansen, Randal Schwartz: Programming Perl. O'Reilly, 1996. ISBN 1-56592-149-6. http://www.perl.com/

Richard Sproat: Morphology and Computation. Massachusetts Institute of Technology; Cambridge, Massachusetts, 1992. ISBN 0-262-19314-0.

Jan Hajič: Unification Morphology Grammar (PhD thesis). Univerzita Karlova, Praha, 1994

Stuart Shieber: An Introduction to Unification-based Approaches to Grammar. CSLI Lecture Notes No. 4, Stanford, California, 1986

Sandra Kübler, Ryan McDonald, Joakim Nivre: Dependency Parsing. Morgan and Claypool Publishers; 2009. ISBN 978-1-59829596-2.

Christopher D. Manning, Hinrich Schütze: Foundations of Statistical Natural Language Processing. The MIT Press, Cambridge, Massachusetts, 1999. ISBN 0-26213-360-1.

Media and tools:computer training room with access to the internet and to Linux machines, Perl programming language 5.8 or higher, dataprojector

Further information:
No time-table has been prepared for this course
The course is a part of the following study plans:
Data valid to 2022-09-27
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/en/predmet23046905.html