ERROR ANALYSIS IN ENGLISH-INDONESIAN MACHINE TRANSLATE

Abstract

Since the advent of the 21st century, there have been a lot of developments and new technologies have been
introduced which have made life more convenient and simple. Although not appropriate for all situations,
machine translation (MT) is now being used by many translators to ease their work. Many others use MT to get a
quick grasp of foreign text that they would not understand. The quality of Google Translate depends on the
number of human translated texts searched by Google Translate. Therefore, the quality of the translation has
been considered far from perfection. Thus in order to evaluate the quality of machine translation, error analysis
has been suggested to be conducted. This paper presents the results of a research study focusing on the types of
Google translation errors found in the English translation of procedural text. The purposes of this paper are (i)
the results of English-Indonesian machine translation, categorizing errors in machine translation into 3 types:
semantic errors, syntax errors and morphology errors, and (ii) to describe the dominant kind of translation error
produced by Google Translate. This study revealed that The most frequently occurring errors were form category
of sematic (i.e., 44 errors out of 97 or 45.36%). Syntax errors ranked second (i.e. 34 errors out of 97 or 35.05%)
and morphology errors ranked third (i.e., 19 errors out of 97 or 19.59%).  
 
Keywords: machine-translate, error analysis, English, Indonesian