magistrsko delo
Jani Dugonik (Author), Janez Brest (Mentor), Borko Bošković (Co-mentor)

Abstract

V magistrskem delu se bomo osredotočili na uglaševanje sistema za strojno prevajanje. V okviru tega bomo vzpostavili sistem za strojno prevajanje, ki temelji na statističnih modelih. Omejili se bomo na prevajanje iz slovenščine v angleščino. Rezultate bomo ocenili z metriko BLEU. Pričakujemo, da bo naš pristop primerljiv z ostalimi metodami.

Keywords

strojno prevajanje;statično strojno prevajanje;jezikovni modeli;evolucijski algoritmi;uteži;uglaševanje;optimizacija;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [J. Dugonik]
UDC: 004.5:004.93(043.2)
COBISS: 17150998 Link will open in a new window
Views: 1907
Downloads: 164
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: TUNING PARAMETERS IN STATISTICAL MACHINE TRANSLATION
Secondary abstract: In this master's thesis, we will focus on tuning the machine translation system. In this context, we will establish the machine translation system based on statistical models. We will confine ourselves to translating from Slovene to English. The results will be evaluated by the BLEU metric. We expect that approach is comparable to other tuning methods.
Secondary keywords: machine translation;statistical machine translation;language model;evolutionary algorithm;weights;tuning;optimization;
URN: URN:SI:UM:
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages: XII, 51 f.
ID: 8726476