English-Indonesian crisis translation: accuracy and adequacy of Covid-19 terms translated by three MT tools
This study focuses on one basic question: how accurate and adequate are the three MT tools, namely Google Translate, Bing and Systran, in generating Covid-19 terms? It measures mainly the accuracy and adequacy of Covid-19 terms translated by three popular MT tools between English and Indonesian. Data analysis is conducted manually through human evaluation toward translation products by using a translation rubric. The assessment includes several samples covering the level of words, sentences and paragraphs. All samples are purposively retrieved from the Coronavirus Corpus and are translated by using the three MT tools. Two raters are involved to analyze texts at sentence and paragraph levels. The raters are used to provide the credibility of translation texts analysis. Results showed that the three MT tools produce different language accuracy and adequacy in revealing COVID-19 terms. Translating noun and pronoun in particular context from English into Indonesian language still remains unclear. This may affect paragraph cohesion. Furthermore, even though these MT tools successfully translate a number of English words into Indonesian, several of the words cited are officially absent in the Great Indonesian Dictionary. This gap raises confusion for Indonesian readers whose English is not sufficient to understand the lexical meaning. In this case, the study highlights the importance of updating the words data base. As this article implements an evaluation translation method, the goal is to produce some recommendations that may be useful for several parties: reader of target language, MT’s developer, linguist and government.