Knjižnica Filozofskog fakulteta
Sveučilišta u Zagrebu
Faculty of Humanities and Social Sciences Institutional Repository

Metodologija izgradnje paralelnih korpusa i ekstrakcije specifične terminologije


Downloads per month over past year

Kukulj, Petar. (2018). Metodologija izgradnje paralelnih korpusa i ekstrakcije specifične terminologije. Diploma Thesis. Filozofski fakultet u Zagrebu, Department of Information Science. [mentor Seljan, Sanja].

PDF (Croatian)
Download (768kB) | Preview


This paper demonstrates the methodologies of corpus building and terminology extraction. The first part provides a theoretical background and describes the development of corpora and corpus analysis tools, as well as the process of preparing a corpus for analysis. A description of the carried out research follows in which the collected English and Croatian sports rulebooks were aligned and used to build a parallel corpus using Sketch Engine, an online corpus tool. The same tool was used for the extraction of specific terminology, the results of which are discussed at the end of the paper.

Item Type: Diploma Thesis
Uncontrolled Keywords: parallel corpus, english language, croatian language, domain-specific terminology, sport
Subjects: Information sciences
Departments: Department of Information Science
Supervisor: Seljan, Sanja
Date Deposited: 04 Feb 2019 12:17
Last Modified: 04 Feb 2019 12:17

Actions (login required)

View Item View Item