Graduate School

Computational Linguistics

This course is part of the programme:
Cognitive science of language Third Level

Objectives and competences

The course provides an overview of the linguistic theory in the domain of computational linguistics. The course aims to establish a necessary level of knowledge, on the basis of which students will be able to conduct their own research under the mentor’s supervision.

Competences:

  • Ability of critical thinking about selected topics in computational linguistics
  • Ability to identify interesting and theoretically significant problems in computational linguistics

Prerequisites

The knowledge of linguistics based on the previous course curriculum in this program.

Content (Syllabus outline)

The following topics will be covered:

  • Natural language processing
  • Modeling of natural language syntax
  • Artificial intelligence

Intended learning outcomes

Basic knowledge of computational linguistics, including corpus-based and computer-intensive methods in linguistic research.

Readings

  • Daniel Jurafsky in James H. Martin. 2000. Speech and Language Processing. Prentice Hall.
  • W. Bruce Croft in John Lafferty (ur.). 2003. Language Modeling for Information Retrieval. Kluwer Academic Publishers.
  • Članki iz znanstvenih revij, ki pokrivajo to področje (Computational Linguistics, Information Retrieval, Artificial Intelligence, Machine Learning, Journal of Artificial Intelligence Research, Natural Language Engineering, Machine Translation)

Assessment

Homework assignments and final term paper (50% / 50%).

Lecturer's references

Assistant professor of Linguistics at the University of Gorica.

Bibliography:

1. ERJAVEC, Tomaž. 2012. MULTEXT-East : morphosyntactic resources for Central and Eastern European languages. Language resources and evaluation, ISSN 1574-020X, vol. 46, no. 1, str. 131-142.

2. POLLAK, Senja, TRDIN, Nejc, VAVPETIČ, Anže, ERJAVEC, Tomaž. 2012. NLP web services for Slovene and English : morphosyntactic tagging, lemmatisation and definition extraction. Informatica, ISSN 0350-5596, vol. 36, no. 4, str. 441-449.

3. ERJAVEC, Tomaž. Posodabljanje starejše slovenščine. 2013. Uporabna informatika, ISSN 1318-1882, letn. 21, št. 4, str. 186-195.

4. HMELJAK SANGAWA, Kristina, ERJAVEC, Tomaž. 2012. JaSlo : integration of a Japanese-Slovene bilingual dictionary with a corpus search system. Acta linguistica asiatica, ISSN 2232-3317, vol. 2, no. 3, str. 125-140.

5. ERJAVEC, Tomaž. Korpusi in konkordančniki na strežniku nl.ijs.si. 2013. Slovenščina 2.0, ISSN 2335-2736, št. 1, str. 24-49.

University course code: 3JEZ025

Year of study: 1

Course principal:

ECTS: 3

Workload:

  • Lectures: 20 hours
  • Other: 70 hours

Course type: elective

Languages: english

Learning and teaching methods:
• lectures • individual work under supervision of the lecturer responsible for the course