Abstract

We describe a mixture-model approach to adapting a Statistical Machine Translation System for new domains, using weights that depend on text distances to mixture components. We investigate a number of variants on this approach, including cross-domain versus dynamic adaptation; linear versus loglinear mixtures; language and translation model adaptation; different methods of assigning weights; and granularity of the source unit being adapted to. The best methods achieve gains of approximately one BLEU percentage point over a state-of-the art non-adapted baseline system. 1

Citations

2168	Indexing by latent semantic analysis - Deerwester, Dumais, et al. - 1990
992	BLEU: A Method for Automatic Evaluation of Machine Translation - Papineni, Roukos, et al. - 2002
612	Statistical Methods for Speech Recognition - Jelinek - 1997
282	Lattice-based minimum error rate training for statistical machine translation - Macherey, Och, et al. - 2008
142	A cache-based natural language model for speech recognition - Kuhn, Mori - 1990
113	The mathematics of Machine Translation: Parameter estimation - Brown, Pietra, et al. - 1993
77	Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models - Iyer, Ostendorf - 1996
44	Improvements in phrase-based statistical machine translation - Zens, Ney - 2004
28	On the dynamic adaptation of stochastic language models - Kneser, Steinbiss - 1993
26	A discriminative global training algorithm for statistical mt - Tillmann, Zhang - 2006
25	Adaptation of the translation model for statistical machine translation based information retrieval - Hildebrand, Eck, et al. - 2005
21	Dynamic nonlocal language modeling via hierarchical topic-based adaptation - Florian, Yarowsky - 1999
20	Language model adaptation for statistical machine translation with structured query models - Zhao, Eck, et al. - 2004
4	Self-training for machine translation - Ueffing - 2006
2	The NiCT-ATR statistical machine translation system for the IWSLT 2006 evaluation - Zhang, Yamamoto, et al. - 2006
1	Phrasetable smoothing for statistical machine translation - Hastie, Friedman - 2006