The Accuracy and Shortcomings of Google Translate Translating English Sentences to Indonesian
| Autor: | Adi Sutrisno |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Google Translate
Memsource Statistical Machine Translation English-Indonesian Translation Sentence-Pair Matrix Grammar Computer science media_common.quotation_subject Linguistics language.human_language SocArXiv|Education Indonesian bepress|Education Morpheme Noun language ComputingMethodologies_DOCUMENTANDTEXTPROCESSING Computational linguistics media_common |
| DOI: | 10.31219/osf.io/su3fk |
| Popis: | Google Translate is a free and practical online translation service that allows millions of people around the globe to translate words, phrases, sentences, and paragraphs into an intended target language. However, in 2015, some Google Translate users in Indonesia, filed complaints, asserting that the machine was often inaccurate, speculating that it could only translate languages at the micro-level of words and phrases, rather than complete sentences or paragraphs. This research works to examine the accuracy as well as the shortcomings of Google Translate, in the context of English to Indonesian translations, in order to critically engage the complaints made by Google users. For the purpose of this study, 80 English sentences were translated using Google Translate and assessed for accuracy using a table adapted from Memsource criteria. Both the original sentences and their translated versions were analyzed using a sentence pair matrix to determine the machine’s failings and areas for improvement. The results challenged those initial speculations which suggested Google Translate is only effective with words and phrases. On the contrary, Memsource proved to be a useful tool in demonstrating a reasonable level of accuracy, accurately translating 60.37% of Indonesian-English sentences and vice versa. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|