Automated layout preservation in cross language translation of document: an integrated approach and implementation

Abstract

Layout refers to format and placement of content in a document. Cross language document translation is a well known problem and is addressed widely. Such translations usually remain unsuccessful in preserving original format of document because of typographical differences across the script of different languages. To make translated document look aesthetically identical to the original document, preservation of layout is essential. In this paper, we propose an integrated approach to solve various problems that arise during the process of translation pertaining to the layout of document like content flow, table of content, maintaining relative position and aesthetics of content.