Improving Statistical Machine Translation Efficiency by Triangulation

@inproceedings{Chen2008ImprovingSM,
  title={Improving Statistical Machine Translation Efficiency by Triangulation},
  author={Yu Chen and Andreas Eisele and Martin Kay},
  booktitle={LREC},
  year={2008}
}
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model that enlarges the search space for the decoder, and consequently requires more time and more resources to translate. This paper describes an attempt to reduce the model size by filtering out the less probable entries based on testing correlation using additional training data in an intermediate third language. The… CONTINUE READING