Language Statistical Machine Translation Muna to Indonesia Language

Abstract

In this rapid technological development, there are still at least some machine translators from regional languages ​​to Indonesian. Therefore, this paper discusses to make a statistical translation machine for the Muna language into Indonesian because at least there are still at least a Muna translation machine into Indonesian. The approach used a statistically based using parallel corpus. In this study, the data taken came from a book entitled Folklore of Buton and Muna in Southeast Sulawesi and several folklore articles on the internet. The number of parallel corpus used is 1050 sentence lines and the monolingual corpus is 1351 sentence lines. The scenarios that will be carried out in this experiment are divided into two scenarios. Scenario 1 is testing on the parallel corpus (training) which is tested using the available sentence lines and these sentence lines will be added to each experiment, while the rest of the sentence lines that are owned will be used in the parallel corpus (testing). In scenario 2, the test is carried out by comparing the lines of the monolingual corpus sentences after subtracting and adding sentences. In order for scenario 2 to run, accuracy is needed in scenario 1 which is the best. The test was carried out 6 times using BLEU (Bilingual Evaluation Understudy) tools. From the results of the tests carried out, the best accuracy value is 29.83%.