Applying Pairwise Ranked Optimisation to Improve the Interpolation of Translation Models

In Statistical Machine Translation we often have to combine different sources of parallel training data to build a good system. One way of doing this is to build separate translation models from each data set and linearly interpolate them, and to date the main method for optimising the interpolation weights is to minimise the model perplexity on a heldout set. In this work, rather than optimising for this indirect measure, we directly optimise for BLEU on the tuning set and show improvements in average performance over two data sets and 8 language pairs.