5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Accelerated DP Based Search for Statistical Translation

C. Tillmann, S. Vogel, Hermann Ney, A. Zubiaga, H. Sawaf

Lehrstuhl für Informatik VI, RWTH Aachen, Germany

In this paper, we describe a fast search algorithm for statistical translation based on dynamic programming (DP) and present experimental results. The approach is based on the assumption that the word alignment is monotone with respect to the word order in both languages. To reduce the search effort for this approach, we introduce two methods: an acceleration technique to eficiently compute the dynamic programming recursion equation and a beam search strategy as used in speech recognition. The experimental tests carried out on the Verbmobil corpus showed that the search space, measured by the number of translation hypotheses, is reduced by a factor of about 230 without affecting the translation performance.

Full Paper

Bibliographic reference.  Tillmann, C. / Vogel, S. / Ney, Hermann / Zubiaga, A. / Sawaf, H. (1997): "Accelerated DP based search for statistical translation", In EUROSPEECH-1997, 2667-2670.