L10N Journal

Introduction

2025-03-03T22:25:37+01:00

Introduction to the issue Slovak Research on Localization 3.

Comparing Machine Translation Effectivity of Selected Engines from English into Slovak on the Example of a Scientific Text

2025-03-03T22:33:19+01:00

In the current age of rapid globalization and technological advancement, it is important to pay attention to machine translation engines. With the rise of artificial intelligence and machine learning, new and improved translation tools are emerging that promise more accurate and faster results. This study focuses on a comparison of the translations (from English to Slovak language) of three prominent tools: Google Translate, DeepL, and the new ChatGPT model. The free versions of these tools are used, except for ChatGPT where we also look at version 4.0, which, at time of writing, is the paid version. The study places emphasis on their capabilities and limitations in translating a specialized text. In the case of the ChatGPT model, the focus is also on how the glossary affects its translation quality. An analysis of not only the final translations but also of the underlying processes and technologies behind these tools is performed. The analysis and comparison of the translation quality of these tools are performed using the TAUS organization’s template for evaluating the quality of machine translations. The key objective is to contribute to a better understanding of the advantages and disadvantages of these translation tools.

Consistency Analysis of Slovak Minecraft Video Game Terminology in Novels and Original Video Games

2025-03-03T22:38:02+01:00

This article examines the Slovak translations of fiction based on the video game Minecraft, with a focus on the adherence to the game’s official terminology. The study aims to determine whether the terminology from the original game has been consistently applied in the translated fiction. The article begins by outlining key theoretical concepts related to video game terminology before presenting an analysis of the selected sample. The findings are discussed in terms of the accuracy of Slovak translations in relation to the official Minecraft terminology across six books. The Slovak translators under review are Slavomír Hrivnák, Lukáš Ondrejkovič, and Šimon Kotvas. The central research question explores the extent to which the translators preserved the game’s terminology in their translations of the fiction.

Comparing the Efficiency of Source Text Pre-editing vs. Machine Translation Post-editing

2025-03-03T22:52:56+01:00

As machine translation (MT) becomes increasingly embedded in professional workflows, researchers explore ways to improve quality and efficiency. Although neural MT systems like DeepL and Google Translate improve fluency, they still require human intervention. Two key strategies are pre-editing (PrE), which modifies the source text before MT to reduce errors, and post-editing (PoE), which refines MT output to meet quality standards.
This study compares PrE and PoE in MT workflows through a controlled experiment involving 20 translation students. One group used PoE alone, while the other combined PrE and PoE. Translation quality was assessed using the TAUS Dynamic Quality Framework, with time efficiency also analyzed.
Findings show PoE alone accelerates the process but increases error rates, particularly in accuracy and fluency. PrE enhances translation quality by reducing errors and cognitive load during PoE, though it requires more time upfront. The combination of PrE and PoE produced the highest-quality translations, suggesting that integrating PrE improves accuracy and consistency. These results highlight the importance of combining human expertise with MT to improve workflows, balancing speed and quality in professional translation.

Machine Translation Quality Based on TER Analysis from English into Slovak

2025-03-03T22:42:57+01:00

Translators are facing increased demand for their services and are increasingly required to utilize tools that can help them save time and increase their efficiency. Neural machine translation (NMT) has become the leading technology in the translation industry, and its utilization promises efficiency gains. However, this is not as straightforward as it may seem, and actual efficiency gains depend on a number of variables: the quality of the NMT output, the translator’s skills, time, and the effort the translator expends on post-editing. This paper aims to analyze the number of edits required for the NMT output to meet quality requirements and determining the acceptability threshold of the neural machine translation output for post-editing based on this number. From a methodological perspective, the study uses TER, an automatic machine translation evaluation metric calculating the smallest edit distance required, to assess the number of edits needed. By analyzing samples from two experiments, it was found that with the TER score between 39% and 42.5%, i.e., when 39-42.5% of the machine translation output needs editing, post-editing ceases to be beneficial, and it is more efficient for the machine translation output with such score to be translated from scratch.

Final Variable

2025-03-03T22:46:24+01:00

The Final Variable section introduces the following publications:

Localization in Translation;

User-Centric Studies in Game Translation and Accessibility;

Automating Translation.