Analysing the Effect of Out-of-Domain Data on SMT Systems
Barry Haddow, Philipp Koehn · Edinburgh Research Explorer (University of Edinburgh) · 2012
In statistical machine translation (SMT), it is known that performance declines when the training data is in a different domain from the test data. Nevertheless, it is frequently necessary to supplement scarce in-domain training data with out-of-domain data. In this paper, we first try to relate the effect of the out-of-domain data on translation performance to measures of corpus similarity, then we separately analyse the effect of adding the out-of-domain data at different parts of the training pipeline (alignment, phrase extraction, and phrase scoring). Through experiments in 2 domains and 8 language pairs it is shown that the out-of-domain data improves coverage and translation of rare words, but may degrade the translation quality for more common words.