[projekt]
Daniel Hari (Author), Mirjam Sepesy Maučec (Mentor), Gregor Donaj (Co-mentor)

Abstract

V projektni nalogi so predstavljene vrste strojnega prevajanja, ki so vgrajene v različne prevajalnike. Ti prevajalniki omogočajo, da se posamezna beseda ali daljše besedilo na podlagi izvedbe določenih algoritmov samodejno prevede iz izvornega jezika v ciljni jezik. Poznamo več načinov strojnega prevajanja, ki jih v nalogi tudi predstavimo. Vsako strojno prevajanje se razlikuje po načinu prevajanja oz. svojih značilnostih, različni načini prevajanja pa imajo tudi določene skupne lastnosti, kot sta sprotno učenje in iskanje dobrih prevodov v slovarjih ali bazah podatkov, ki pripomorejo k bolj natančnemu prevodu same besede oz. besedila. Naloga je sestavljena iz teoretičnega in praktičnega dela. V teoretičnem delu je predstavljen pregled načinov prevajanja, v praktičnem delu pa analiza kakovosti prevajanja posameznih prosto dostopnih prevajalnikov.

Keywords

strojno prevajanje;strojni prevajalniki;slovarji;korpus;strojno učenje;statistični pristop;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [D. Hari]
UDC: 621.39
COBISS: 22111510 Link will open in a new window
Views: 964
Downloads: 154
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Overview of free machine translation systems
Secondary abstract: The thesis presents the types of machine translation that are built into machine translation systems. These systems enable us to translate a word or a text from the source language into the target language based on some algorithms. We know several ways of machine translation, which we also presented in the project. Each machine translation differs in its own form of translation or its characteristics. However, different systems have also some common attributes such as real-time learning and the search for good translations in dictionaries and databases which contribute to a more acceptable translation of the word or text itself. The project has a theoretical part and a practical part. In the former, we overview machine translation approaches. In the latter, we analyze different translation systems in terms of quality of produced translations.
Secondary keywords: Machine translation;machine translator;dictionary;corpus;machine learning;statistical approach.;
URN: URN:SI:UM:
Type (COBISS): Diploma project paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Telekomunikacije
Pages: X, 91 f.
ID: 10949990