Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

3 Slovenská reč (Slovak Language)

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

STROJOVÝ PREKLAD ZALOŽENÝ NA NEURÓNOVÝCH SIEŤACH – SĽUBNÁ CESTA PREKLADU Z ANALYTICKÝCH JAZYKOV DO FLEKTÍVNEJ SLOVENČINY?

100%

Petráš P. , Munková D.

Slovenská reč (Slovak Language)

2023

tom 88

nr 1

74 – 89

In this paper, we deal with the issues of machine translation based on neural network. We explain the fundamental principles of this approach to automatic translation. Based on the analysis of statistical and neural machine translations from English into Slovak, we compare the quality, and/or the qualitative shifts after changing the approach to machine translation, from statistical to neural networks. The results reveal that neural machine translation achieves better results in fluency and grammatical correctness of translation, but the representation of semantically inadequate translations increases in examined corpus of journalistic texts.

(NIELEN) LINGVISTICKÝ POHĽAD NA STROJOVÝ PREKLAD (NA PRÍKLADE PREKLADOV TEXTOV TECHNICKEJ DOKUMENTÁCIE Z ANGLIČTINY DO SLOVENČINY)

100%

Petráš P. , Munková D.

2019

tom 84

nr 3

258 – 287

Machine translation is currently a very widespread translation technology, translating from one language to another. In the first part of the paper, we explain the basic principles of the machine translation process. We also identify the reasons behind their error rate, and the influence of grammatical differences of the translated languages and type of translated texts on the error rate. In the second, exemplification part of the paper, we categorize and analyse errors that have occurred in the machine translation of technical documentation from English to Slovak. We believe that our analysis will prove the perspective and usability of machine translation, especially in texts that are not difficult to translate (texts with stereotyped expressions using schematic constructions, sentences, such as technical documentation), despite the errors which occurred in translations (the analysis of the machine translation output showed that not every error is equally serious with regard to its influence on the adequate transfer of the meaning of the source text into the target text).

POROVNANIE STROJOVÉHO, POSTEDITOVANÉHO A ĽUDSKÉHO PREKLADU TECHNICKEJ DOKUMENTÁCIE ZO SLOVENČINY DO NEMČINY

80%

Hudecová E. , Stahl J. , Benková L. , Munková D.

Slovenská reč (Slovak Language)

2021

tom 86

nr 2

192 – 207

The article emphasizes the possibilities of machine translation and post-editing in relation to specialised, technical texts. We compare machine translation, post-edited machine translation and reference human translation of technical documentation translated from Slovak to German. The main focus dwells on lexical similarity of machine translation with regard to the reference human translation, as well as on the reasons for differences between the two by means of TER and HTER scores. We assume that the reference human translation and post-edited machine translation will show the same or almost the same error rate. We pay special attention to error rates between 0 and 10%, where there might have been differences between the reference human translation and the machine translation but the post-editor marked them as correct, when they met their communicative function.