DFKI-LT - Morpheme- and POS-based IBM1 scores and language model scores for translation quality estimation

Maja Popovic
Morpheme- and POS-based IBM1 scores and language model scores for translation quality estimation
1 Proceedings of the Seventh Workshop on Statistical Machine Translation, Pages 133-137, Montreal, QC, Canada, Association for Computational Linguistics, 6/2012
 
We present a method we used for the quality estimation shared task of WMT 2012 involving IBM1 and language model scores calculated on morphemes and POS tags. The IBM1 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.
 
Files: BibTeX, quality.pdf