A Study on the Accuracy of Human Translation Output and Post-Edited Google Translate Output as far as English and Sinhalese Language Pair is considered: With Special Reference to Selected Literary and Non-literary Documents
- August 5, 2019
- Posted by: RSIS
- Category: Language and Literature
International Journal of Research and Innovation in Social Science (IJRISS) | Volume III, Issue VII, July 2019 | ISSN 2454–6186
Gunathilaka D. D. I. M. B. 1 and Ariyaratne W. M.2
1 & 2 Department of Languages, Sabaragamuwa University of Sri Lanka, Belihuloya, Sri Lanka
Abstract: – With the rapid growth in global communication and commerce, the importance of translation has skyrocketed and the involvement of technology is determined as a necessity to make the workload in translation easier and cheaper. However, later it was proved that machines can not alone perform a faithful service in translation and consequently, translators offer their corporation as post-editors in Machine Translation (MT) (Post-Editing (PE)) to make the translation process as quick, accurate, and effective as possible. Focusing on this matter, this research investigated the fidelity of Machine-Aided Translation (MAT) measuring the accuracy of post-edited Google Translate (GT) output compared to the accuracy achieved in Human Translation (HT) from English into Sinhalese referring number of selected literary and non-literary texts. This study, therefore involves in finding which mode is most appropriate in producing an accurate translation while aiming at observing the barriers faced in HT and PE, advantages and disadvantages of HT and PE, and the importance of human assistance in machine translation. Primary data were collected by affiliating four professional translators and the collected data were analyzed under the dichotomy of Generative Grammar introduced by Noam Chomsky. The marking scale of the Canadian Translators, Terminologists, and Interpreters Council (CTTIC) is referred for measuring the accuracy of the target texts considering the error analysis. This study has finally identified that though both modes can produce accurate literary and non-literary translations, HT is the most appropriate method for literary translation in terms of creativity and PE for non-literary translation in terms of productivity which means that PE does not suit for all scenarios and proves machines are still helpless without human intervention in the field of translation.
Keywords: Accuracy, Creativity, Human Translation, Literary and Non-literary Translation, and Post-Editing
