Towards an effective toolkit for translators

Andreas Eisele, Christian Federmann, James Hodson

In: Proceedings of the ASLIB Translating and the Computer Conference 31. Translating and the Computer Conference (TC-31) November 19-20 London United Kingdom ASLIB 2009.


As advances in the field of machine translation (MT) continue to allow for greater distribution of multi-lingual information, an increasing number of web based tool-kits are being developed. However, these systems (such as Google's Translator Tool-kit) have failed to satisfy the translation community due to a fundamental misunderstanding of the way translators work. The aim of this project has been to reduce the time that translators spend on the whole transfer process - by realising that an MT core can provide much more than a raw translation, even at this relatively early stage of its development. This paper evaluates the shortcomings of existing systems and proposes a new integrated online-toolkit that addresses these limitations based on an understanding of the most significant and unnecessary struggles between translators and MT systems.


TatC31.pdf (pdf, 111 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence