Morpheme- and POS-based IBM1 and language model scores for translation quality estimation
Maja Popović · Workshop on Statistical Machine Translation · 2012
We present a method we used for the quality estimation shared task of WMT 2012 involving IBM 1 and language model scores calculated on morphemes and POS tags. The IBM 1 scores calculated on morphemes and POS-4grams of the source sentence and obtained translation output are shown to be competitive with the classic evaluation metrics for ranking of translation systems. Since these scores do not require any reference translations, they can be used as features for the quality estimation task presenting a connection between the source language and the obtained target language. In addition, target language model scores of morphemes and POS tags are investigated as estimates for the obtained target language quality.