The increasing interest in the statistical approach to Machine Translation is due to the development of effective algorithms for training the probabilistic models proposed so far. However, one of the problems with Statistical Machine Translation is the design of efficient algorithms for translating a given input string. For some interesting models, only (good) approximate solutions can be found. Recently a Dynamic- Programming-like algorithm has been introduced which computes approximate solutions for some models. These solutions can be improved by using an iterative algorithm that refines the successive solutions and uses a smoothing technique for some probabilistic distribution of the models based on an interpolation of different distributions. The technique resulting from this combination has been tested on the "Tourist Task" corpus, which was generated in a semi-automated way. The best results achieved were a translation word-error rate of 9.3% and a sentence-error rate of 44.4%.
Cite as: García-Varea, I., Casacuberta, F., Ney, H. (1998) An iterative, DP-based search algorithm for statistical machine translation. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0209, doi: 10.21437/ICSLP.1998-567
@inproceedings{garciavarea98_icslp,
author={Ismael García-Varea and Francisco Casacuberta and Hermann Ney},
title={{An iterative, DP-based search algorithm for statistical machine translation}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0209},
doi={10.21437/ICSLP.1998-567}
}