Paper: Applying Pairwise Ranked Optimisation to Improve the Interpolation of Translation Models

ACL ID N13-1035
Title Applying Pairwise Ranked Optimisation to Improve the Interpolation of Translation Models
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2013
Authors

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 inter- polate them, and to date the main method for optimising the interpolation weights is to min- imise the model perplexity on a heldout set. In this work, rather than optimising for this indi- rect measure, we directly optimise for BLEU on the tuning set and show improvements in average performance over two data sets and 8 language pairs.