Linguistic Engineering - Constructions

General data

Course ID:	1000-2M07LK
Erasmus code / ISCED:	11.303 The subject classification code consists of three to five digits, where the first three represent the classification of the discipline according to the Discipline code list applicable to the Socrates/Erasmus program, the fourth (usually 0) - possible further specification of discipline information, the fifth - the degree of subject determined based on the year of study for which the subject is intended. / (0612) Database and network design and administration The ISCED (International Standard Classification of Education) code has been designed by UNESCO.
Course title:	Linguistic Engineering - Constructions
Name in Polish:	Inżynieria lingwistyczna - konstrukcje
Organizational unit:	Faculty of Mathematics, Informatics, and Mechanics
Course groups:	(in Polish) Przedmioty obieralne na studiach drugiego stopnia na kierunku bioinformatyka Elective courses for Computer Science and Machine Learning
ECTS credit allocation (and other scores):	(not available) Basic information on ECTS credits allocation principles: the annual hourly workload of the student’s work required to achieve the expected learning outcomes for a given stage is 1500-1800h, corresponding to 60 ECTS; the student’s weekly hourly workload is 45 h; 1 ECTS point corresponds to 25-30 hours of student work needed to achieve the assumed learning outcomes; weekly student workload necessary to achieve the assumed learning outcomes allows to obtain 1.5 ECTS; work required to pass the course, which has been assigned 3 ECTS, constitutes 10% of the semester student load. view allocation of credits
Language:	English
Type of course:	elective monographs
Short description:	The aim of the lecture is to present practical methods and techniques of natural language processing. These techniques, mainly the techniques of syntactic and semantic processing, will be illustrated with specific tasks (such as: Information Extraction, Dialogue Systems, etc.), on the basis of English and Polish. The lecture focuses on high-level largely language-dependent methods. This lecture is to a large extent independent of and complementary to the lecture Linguistic Engineering ? Constructions.
Full description:	1. Introduction. Terminology (Linguistic Engineering, Computational Linguistics, NLP, HLT, etc.), history, applications, two paradigms (symbolic and statistical). (1 lecture) 2. Types of syntactic processing, shallow parsing, parsing as tagging (lexical disambiguation). (1 lecture) 3. Shallow parsing with regular grammars, cascades of regular grammars. (1 lecture) 4. Information extraction. (1 lecture) 5. Deep parsing, context-free grammars and parsers. (1-2 lectures) 6. Treebanks and stochastic parsers. (1 lecture) 7. Dependency grammars and parsers. (1 lecture) 8. Unification-based grammars and parsers (DCG, PATR-II, HPSG). (1 lecture) 9. Semantics: lexical and compositional, meaning representation, semantic formalisms. (1 lecture) 10. Montague semantics and/or Discourse Representation Theory. (1 lecture) 11. Semantics in context-free, dependency and unification-based grammars. (1-2 lectures) 12. Text generation and traditional approaches to machine translation. (1 lecture) 13. Discourse representation, dialogue systems. (1 lecture) The course will be given in Polish, if no non-Polish speaking students register for it.
Bibliography:	1. Steven Bird, Ewan Klein i Edward Loper 2009, "Natural Language Processing - Analyzing Text with Python and the Natural Language Toolkit", http://www.nltk.org/book. 2. Daniel Jurafsky i James H. Martin 2009, "Speech and Language Processing", Prentice-Hall (2nd edition). 3. Sandra Kübler, Ryan McDonald i Joakim Nivre 2009, „Dependency Parsing”, Morgan & Claypool. 4. Adam Przepiórkowski 2008, "Powierzchniowe przetwarzanie języka polskiego", EXIT, Warszawa.

This course is not currently offered.

Course descriptions are protected by copyright.
Copyright by University of Warsaw.