Alena A. Zhivotova, Victor D. Berdonosov

Komsomolsk-na-Amure State University

The authors study the process of text translation, particularly the method of optimizing pre-editing as a way to improve the quality of machine translation into English for Russian-language highly specialized texts. The paper considers the mathematical model of translation process and machine translation task formulation, proposes a new theory for probabilistic estimation of translation task complexity, provides the formulation and solution of optimizing pre-editing task, describes data preparation methodology for training automatic optimizing pre-editing model. As the research result the software package for optimizing pre-editing of Russian-language texts is developed. The software package has been developed using resources of the Center for Scientific Equipment Collective Use "Center for Processing and Storage of Scientific Data of the Far Eastern Branch of the Russian Academy of Sciences". Data for models training and validation are provided by Translation Agency FIAS-Amur Co., Ltd. Software package testing has proved the effectiveness of the proposed methods for improving the quality of machine translation of highly specialized Russian-language texts into English.

machine translation, optimizational pre-editing, translation task complexity, translation quality