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

Abstract

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.