Investigating Core Technologies in Computer-aided Multi-lingual Translation Memory

DOI

10.2991/erse.2013.56How to use a DOI?

Keywords

multi-lingual translation memory, sentence similarity, TM structure, translation cleaning up.

Abstract

Based on status quo analysis of the current machine translation and computer-aided translation, this study intends to look into the core technologies of multilingual translation memory. This study takes the holistic perspective that views example-based machine translation and computer-aided translation memory as two contrasting and also complementary solutions to account for the complexity and diversity and world languages in translation. Also, Technological solutions to a multi-lingual translation project are discussed in accordance with the problem analyses. Three core technologies are brought into detailed analysis. In calculating sentence similarities, this study argues in favor of a mixed method of minimum edit distance. In structuring a multi-lingual translation memory, an exemplary structure in XML format is proposed. And for translation cleaning up, the routine practice is adjusted to fit a CAT system with a multi-lingual translation memory. This paper ends with a concluding remark of this study and by bringing up the future work.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Huangfu Wei
PY  - 2013/08
DA  - 2013/08
TI  - Investigating Core Technologies in Computer-aided Multi-lingual Translation Memory
BT  - Proceedings of the 2013 International Conference on Educational Research and Sports Education (ERSE 2013)
PB  - Atlantis Press
SP  - 197
EP  - 200
SN  - 1951-6851
UR  - https://doi.org/10.2991/erse.2013.56
DO  - 10.2991/erse.2013.56
ID  - Wei2013/08
ER  -