A Comparative Study of Google Translate Translations: An Error Analysis of English-to-Persian and Persian-to-English Translations

Abstract

Both lack of time and the need to translate texts for numerous reasons brought about an increase in studying machine translation with a history spanning over 65 years. During the last decades, Google Translate, as a statistical machine translation (SMT), was in the center of attention for supporting 90 languages. Although there are many studies on Google Translate, few researchers have considered Persian-English translation pairs. This study used Keshavarzʼs (1999) model of error analysis to carry out a comparison study between the raw English-Persian translations and Persian-English translations from Google Translate. Based on the criteria presented in the model, 100 systematically selected sentences from an interpreter app called Motarjem Hamrah were translated by Google Translate and then evaluated and brought in different tables. Results of analyzing and tabulating the frequencies of the errors together with conducting a chi-square test showed no significant differences between the qualities of Google Translate from English to Persian and Persian to English. In addition, lexicosemantic and active/passive voice errors were the most and least frequent errors, respectively. Directions for future research are recognized in the paper for the improvements of the system.

I Can’t Live Without Google Translate: A Close Look at the Use of Google Translate App by Second Language Learners in Saudi Arabia

“…Groves and Mundt (2015) examined the accuracy of a text produced by Google Translate after being translated from Malay and Chinese into English and found that the text had translation errors. Ghasemi and Hashemian (2016) investigated the errors produced by Google Translate in a translation from English to Persian and vice versa and found no difference in the translation quality, as both ways had errors. This research will discuss all the features of GTA as used by second language learners to translate between Arabic and English, and to investigate the personal histories of these learners with GTA.…”

The Effect of L2 Proficiency on Post-editing Machine Translated Texts

“…Previous research in MT use has centered on analyzing structures that are especially vulnerable to translation errors and mistranslations (Dhakar, Sinha, & Pandey, 2013;Ghasemi & Hashemian, 2016), analyzing written texts by second language (L2) learners who used MT (Lee, 2019;Groves & Mundt, 2015), surveying learners' attitudes and use of MT (Im, 2017;Larson-Guenette, 2013;White & Heidrich, 2013), and searching for pedagogical applications and implementing translation tools in the context of teaching (Correa, 2014;Enkin & Mejías-Bikandi, 2016;Garcia & Pena, 2011). While much has been discussed about the educational implications of translation in L2 writing, it is not yet clear how exactly the learners use and integrate MT in their writing and whether individual learner differences such as proficiency level affect how learners use this online tool.…”

Proceedings of the Combined Workshop on Spatial Language Understanding (

“…There is a strong multilingual community in the broader field of NLP working in many different aspects, such as machine translation (Wu et al, 2016) or multilingual question answering (Gao et al, 2015). Some works dive deep into specific language pairs to evaluate how differences between the languages complicate translation (Alasmari et al, 2016;Gupta and Shrivastava, 2016;Ghasemi and Hashemian, 2016). Several work with Spanish and English specifically (Le Roux et al, 2012;Pla and Hurtado, 2014).…”