Parameter Optimization for Statistical Machine Translation: It Pays to Learn from Hard Examples

@inproceedings{Nakov2013ParameterOF,
  title={Parameter Optimization for Statistical Machine Translation: It Pays to Learn from Hard Examples},
  author={Preslav Nakov and Fahad Al-Obaidli and Francisco Guzm{\'a}n and Stephan Vogel},
  booktitle={RANLP},
  year={2013}
}
Research on statistical machine translation has focused on particular translation directions, typically with English as the target language, e.g., from Arabic to English. When we reverse the translation direction, the multiple reference translations turn into multiple possible inputs, which offers both challenges and opportunities. We propose and evaluate several strategies for making use of these multiple inputs: (a) select one of the datasets, (b) select the best input for each sentence, and… CONTINUE READING