RTM results for Predicting Translation Performance

Ergun Biçici. RTM results for Predicting Translation Performance. In Proc. of the Third Conference on Statistical Machine Translation (WMT18), Brussels, Belgium, November 2018.

With improved prediction combination using weights based on their training performance and stacking and multilayer perceptrons to build deeper prediction models, RTMs become the 3rd system in general at the sentence-level prediction of translation scores and achieve the lowest RMSE in English to German NMT QET results. For the document-level task, we compare document-level RTM models with sentence-level RTM models obtained with the concatenation of document sentences and obtain similar results.