|Title||Improving alignment for SMT by reordering and augmenting the training corpus|
|Publication Type||Conference Paper|
|Year of Publication||2009|
|Authors||Holmqvist, M, Stymne, S, Foo, J, Ahrenberg, L|
|Conference Name||Fourth Workshop on Statistical Machine Translation (WMT09)|
|Conference Location||Athens, Greece|
We describe the LIU systems for English-German and German-English translation in the WMT09 shared task. We focus on two methods to improve the word alignment: (i) by applying Giza++ in a second phase to a reordered training corpus, where reordering is based on the alignments from the first phase, and (ii) by adding lexical data obtained as high-precision alignments from a different word aligner. These methods were studied in the context of a system that uses compound processing, a morphological sequence model for German, and a part-of-speech sequence model for English. Both methods gave some improvements to translation quality as measured by Bleu and Meteor scores, though not consistently. All systems used both out-of-domain and in-domain data as the mixed corpus had better scores in the baseline configuration.