We designed, implemented and assessed ALEPH, a pure example-based machine translation system. It strictly does not make any use of variables, templates or training, does not have any explicit transfer component, and does not require any preprocessing of the aligned examples. It relies on a specific operation: the resolution of analogical equations, that neutralizes translation divergences in an elegant way. Starting only from theoretical results, a system that is state-of-the-art with the top IWSLT 2004 results could be built in six month time. Evaluated on the Unrestricted Data track of IWSLT 2004, our system achieved second place in CE, and third place in JE (with best BLEU for this latter track). For this year's evaluation campaign, the features of the system allowed its immediate application to all possible language pairs in the C-STAR tracks.
Cite as: Lepage, Y., Denoual, E. (2005) ALEPH: an EBMT system based on the preservation of proportional analogies between sentences across languages. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 37-44
@inproceedings{lepage05_iwslt,
author={Yves Lepage and Etienne Denoual},
title={{ALEPH: an EBMT system based on the preservation of proportional analogies between sentences across languages}},
year=2005,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)},
pages={37--44}
}