Journals - MOST Wiedzy

TASK Quarterly

SPECIALIZED FULLY AUTOMATIC MACHINE TRANSLATION SYSTEM DELIVERING HIGH QUALITY OF TRANSLATED TEXTS

Abstract

The paper concerns machine translation systems that form a discipline of computer science and are aimed at writing computer programs that are able to translate text between natural languages. In the paper the author argues that it is not possible to build a machine translation system that would be able to translate any kind of documents with a sufficiently high quality. Instead, the author proposes a specialized machine translation system the aim of which is to translate financial reports concerning the global currency exchange market – forex. For the purpose of building the above mentioned system, the author has proposed his own machine translation method of translation patterns. The translation patterns allow transferring the translation process from the level of single words to the level of words chunks. The translation patterns play a very important role in the case of such an inflectional language as Polish because they make it possible to choose the correct form of Polish translation of foreign phrases depending whether they perform the verb or object function in the sentence. The high quality of the specialized machine translation system developed by the author was proved with many experiments the results of which are demonstrated in the paper. The quality of translation is so high that the Polish translations of English reports from the global currency exchange market can be published on Web pages without any additional changes. Thus, it is possible to totally eliminate the human translator from the process of translation of texts which are highly stereotypical and oriented to a selected and narrow domain.

Keywords:

natural language processing, machine translation, translation patterns

Details

Issue
Vol. 13 No. 4 (2009)
Section
Research article
Published
2009-12-29
Licencja:
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors

MIROSŁAW GAJER

University of Science and Technology, Department of Control Science

Download paper