LIMSI took part in the IWSLT 2011 TED task in the MT track for English to French using the in-house n-code system, which implements the n-gram based approach to Machine Translation. This framework not only allows to achieve state-of-the-art results for this language pair, but is also appealing due to its conceptual simplicity and its use of well understood statistical language models. Using this approach, we compare several ways to adapt our existing systems and resources to the TED task with mixture of language models and try to provide an analysis of the modest gains obtained by training a log linear combination of in- and out-of-domain models.
Cite as: Lavergne, T., Allauzen, A., Le, H.-S., Yvon, F. (2011) LIMSI's experiments in domain adaptation for IWSLT11. Proc. International Workshop on Spoken Language Translation (IWSLT 2011), 62-67
@inproceedings{lavergne11_iwslt,
author={Thomas Lavergne and Alexandre Allauzen and Hai-Son Le and François Yvon},
title={{LIMSI's experiments in domain adaptation for IWSLT11}},
year=2011,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2011)},
pages={62--67}
}