Customizing a banking and finance focused NMT System: An empirical study measuring the effect of controlled language

The industry of translation is developing day by day with technological innovations. These technological innovations make processes easier for the stakeholders of translation service who form the link of the translation service chain, including translators, editors, project managers and people who need translation services. Neural machine translation (NMT) is one of the most up-to-date innovations in the translation industry and NMT has become one of the milestones reshaping the translation industry. The task of NMT system development is mostly left to computer engineers and software experts. Translators often avoid attempts to improve these systems. The first aim of this study is to create an NMT system for banking and finance texts by using the advantage of today's technologies as a translator. In the second part of the study, it has been investigated whether the Controlled Language rules, which have been very popular in recent years, are effective in improving the quality of translations made in NMT system.