Ikasketa automatikoko tekniken erabilgarritasun azterketa euskararako postediziorako gomendio-sistema eraikitzeko

Abstract

The overall machine translation quality available for professional transla-tors working with the Spanish-Basque pair is rather poor, which is a deterrent for its adoption. This work investigates the plausibility of building a comprehensive recom-mendation system to speed up decision time between postediting or translation from scratch using the very limited training data available. First, we build a set of regression models that predict the postediting effort in terms of overall quality, time and edits. Secondly, we build classification models that recommend the most efficient editing ap-proach using postediting effort features on top of linguistic features. Results show high correlations between the predictions of the regression models and the expected HTER, time and edit number values. Similarly, the results for the classifiers show that they are able to predict with high accuracy whether it is more efficient to translate or to postedit a new segment.