The TÜBİTAK statistical machine translation system for IWSLT 2012.
Coşkun Mermer, Hamza Kaya, İlknur Durgar El-Kahlout, Mehmet Ug̃ur Dog̃an · IWSLT · 2012
We describe the T ¨ UBsubmission to the IWSLT 2012 Evaluation Campaign. Our system development focused on utilizing Bayesian alignment methods such as varia- tional Bayes and Gibbs sampling in addition to the standard GIZA++ alignments. The submitted tracks are the Arabic- English and Turkish-English TED Talks translation tasks.