TÜBITAK Turkish-English submissions for IWSLT 2013

Ertugrul Yilmaz, Ilknur Durgar El-Kahlout, Burak Aydin, Zisan Sila Özil, Coskun Mermer
2013 International Workshop on Spoken Language Translation  
This paper describes the T ÜB İTAK Turkish-English submissions in both directions for the IWSLT'13 Evaluation Campaign TED Machine Translation (MT) track. We develop both phrase-based and hierarchical phrase-based statistical machine translation (SMT) systems based on Turkish wordand morpheme-level representations. We augment training data with content words extracted from itself and experiment with reverse word order for source languages. For the Turkish-to-English direction, we use Gigaword
more » ... rpus as an additional language model with the training data. For the English-to-Turkish direction, we implemented a wide coverage Turkish word generator to generate words from the stem and morpheme sequences. Finally, we perform system combination of the different systems produced with different word alignments.
dblp:conf/iwslt/YilmazEAOM13 fatcat:7rovegvqi5b7xmz5ibw3lvz7fq