Introduction to Computational Linguistics

Time: Monday 2pm - 5pm
Venue: Seminar Room, General Linguistics Department, Irinyi Building

This course will introduce students to computational linguistics and natural language processing. During the semester, we will cover the most important research areas of the field such as corpus linguistics, computational morphology, syntax and semantics, as well as applications. Students will have the opportunity to acquire both theoretical and practical knowledge of current issues in computational linguistics through reading assignments and project work.

The class on computational pragmatics will be held on 10 October (Wednesday), 12-13:30 at the Research Group on Artificial Intelligence (same building as usual, 3rd staircase). Let's meet 5 minutes before in the yard.


Course description [pdf]

Coursebook [pdf]

Introduction [slides]

Corpus linguistics [slides]

Speech technology [slides]

Morphology and POS tagging [slides]

Quiz 1 [link] deadline: 24 September [solutions and results]

Syntax [slides]

Semantics [slides]

Wordnets [slides]

Pragmatics [slides]

Information extraction and retrieval [slides]

Quiz 2 [link] deadline: 15 October [solutions and results]

Machine translation [slides]

NLP tools and applications [pdf] - for home studies

Former courses

Nyelvészet az informatikában - informatika a nyelvészetben [Linguistics in Informatics - Informatics in Linguistics]

Time: Wednesday 12pm - 2pm
Venue: Irinyi 221

The course aims at demonstrating how linguistics may contribute to informatics - more specifically, to natural language processing. Furthermore, it will be also shown how informatics may help research in theoretical linguistics. The language of the course is Hungarian.


Course description (in Hungarian) [pdf]

Korpuszok a nyelvészeti kutatásban [Corpora in Linguistic Research]

Time: Thursday 2pm - 4pm
Venue: Mészöly Gedeon seminar room

The course aims at demonstrating how corpora and linguistic databases may be exploited in linguistic research. Steps to construct corpora and gathering language data from them will be also presented in detail. Each student will be required to prepare his/her own corpus during the semester. The language of the course is Hungarian.


Course description (in Hungarian) [pdf]

A számítógépes nyelvfeldolgozás alapjai [Basics of natural language processing]

The course aims at introducing students of arts into natural language processing. The language of the course is Hungarian.


Schedule (in Hungarian) [pdf]

Thematic Training Course on Processing Morphologically Rich Languages

The University of Helsinki and the Research Institute for Linguistics, Hungarian Academy of Sciences hosted a one week training course on computational processing of morphologically rich languages, where I gave a lecture on syntax-morphology interface and its relation to Natural Language Processing.

Syntax seminar

This course offers an introduction to English syntax for 2- and 3-year BA students of English. Topics primarily focus on the practical applications of theoretical knowledge acquired at the Syntax lecture hence it is advised to attend the two courses parallelly. During the semester, two written tests should be completed.


Earlier tests 1
Earlier tests 2