Course title:

Computational linguistics

Course code: PSL218
Course status: Elective
Course leader: Marko Tadić
Course instructor:
Language of instruction: English
Total hours: 8S
Form of instruction: Seminar
ECTS credits: 4

Course content by topics:

Computational linguistics in interaction with: computer processing of natural language, artificial intelligence and speech processing; linguistic levels and computer processing. Procedures and resources: algorithm/statistical approaches; analysis/generating; role of corpora; text segmentation (sentences, words); word level (morphological analysis, tagging, lemmatization); sentence level (syntactic analysis, parsing, sentence element recognition, name recognition); lexical semantics (WordNet) and sentence semantics (FrameNet); machine (assisted) translation; language technologies.

Learning outcomes at course level:

1) To critically evaluate fundamental contemporary approaches to computational linguistics; 2) To define the place of computational linguistics within linguistics; 3) To critically evaluate and explain the practical use of particular methods of computational linguistics in the processing of linguistic material; 4) To explain the importance of the use of computational linguistics methods in collecting and processing linguistic material

Learning outcomes at programme level:

Reading list:

Mitkov, R. (ed.) (2003): The Oxford Handbook of Computational Linguistics. Oxford: Oxford University Press,.; Jurafsky, D. & J. H. Martin (eds.) (2000): Speech and language processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice-Hall: Upper Saddle River, NJ. (http://www.cs.colorado.edu/~martin/slp.html); Manning, C. D. & Schütze, H. (1999): Foundations of Statistical Natural Language Processing. Cambridge, MA MIT Press. (http://www–nlp.stanford.edu/fsnlp/); Hausser, R. R. (2001): Foundations of Computational Linguistics: Human-Computer Communication in Natural Language. Springer Verlag.; Fellbaum, Ch. (1998): Wordnet: An electronic lexical database. MIT Press, Cambridge MA.; Tadić, M.

(2003): Jezične tehnologije i hrvatski jezik. Zagreb: Exlibris.; Tadić, M.; Brozović-Rončević, D.; Kapetanović, A. (2012); Hrvatski jezik u digitalnom dobu / The Croatian Language in the Digital

Age. Springer, Heidelberg. (http://www.meta-net.eu/whitepapers/e-book/croatian.pdf); Tadić, M.; Šojat, K.; Bekavac, B. (2005): Zašto nam treba hrvatski WordNet?« U: Granić, J. (ur.): Semantika prirodnog jezika i metajezik semantike. Zagreb-Split: HDPL, str. 733-743.; Erjavec, T.; Krstev, C.; Petkevič, V.; Simov, K.; Tadić, M.; Vitas, D. (2003): The MULTEXT-East Morphosyntactic Specifications for Slavic Languages. In: Proceedings of the EACL 2003

Workshop on Morphological Processing of Slavic Languages. Budimpešta: ACL, pp. 25-32.; Selected papers from Computational Linguistics journal and LREC Proceedings.

Assessment of student achievement: course attendance Quality assurance mechanism: student survey