Abstract

In statistical machine translation, estimating word-to-word alignment probabilities for the translation model can be difficult due to the problem of sparse data: most words in a given corpus occur at most a handful of times. With a highly inflected language such as Czech, this problem can be particularly severe. In addition, much of the morphological variation seen in Czech words is not reflected in either the morphology or syntax of a language like English. In this work, we show that using morphological analysis to modify the Czech input can improve a Czech-English machine translation system. We investigate several different methods of incorporating morphological information, and show that a system that combines these methods yields the best results. Our final system achieves a BLEU score of.333, as compared to.270 for the baseline word-to-word system. 1

Citations

805	A systematic comparison of various statistical alignment models - Och, Ney - 2003
264	Statistical language modeling using the cmucambridge toolkit - Clarkson, Rosenfeld - 1997
114	Building a Syntactically Annotated Corpus: The Prague Dependency Treebank - Hajič - 1998
67	Statistical machine translation - Al-Onaizan, Curin, et al. - 1999
51	Statistical machine translation with scarce resources using morpho-syntatic analysis - Niessen, Ney - 2004
22	Improving SMT Quality with Morpho-syntactic Analysis - Niessen, Ney - 2000
13	2003. Czech-English dependency-based machine translation - Čerjek, Cuˇrin, et al.
5	Statistical machine translation: The fabulous present and future - Och - 2005
4	The ISI ReWrite Decoder 1.0.0a. Available at http://www.isi.edu/licensed-sw/rewrite-decoder - Marcu, Germann - 2005