TÜBİTAK SMT System Submission for WMT2016
نویسندگان
چکیده
We describe the TÜBİTAK TurkishEnglish machine translation systems submissions in both directions for the WMT 2016: News Translation Task. We experiment with phrase-based and hierarchical phrase-based systems for both directions using word-level and morpheme-level representations for the Turkish side. Finally we perform system combination which results in 0.5 BLEU increase for Turkishto-English and 0.3 BLEU increase for English-to-Turkish.
منابع مشابه
TÜBİTAK - BİLGEM German - English Machine Translation Systems for WMT ’ 13
This paper describes TÜBİTAK-BİLGEM statistical machine translation (SMT) systems submitted to the Eighth Workshop on Statistical Machine Translation (WMT) shared translation task for German-English language pair in both directions. We implement phrase-based SMT systems with standard parameters. We present the results of using a big tuning data and the effect of averaging tuning weights of diff...
متن کاملTÜBİTAK-BİLGEM German-English Machine Translation Systems for W13
This paper describes TÜBİTAK-BİLGEM statistical machine translation (SMT) systems submitted to the Eighth Workshop on Statistical Machine Translation (WMT) shared translation task for German-English language pair in both directions. We implement phrase-based SMT systems with standard parameters. We present the results of using a big tuning data and the effect of averaging tuning weights of diff...
متن کاملThe TÜBİTAK statistical machine translation system for IWSLT 2012
We describe the TÜBİTAK submission to the IWSLT 2012 Evaluation Campaign. Our system development focused on utilizing Bayesian alignment methods such as variational Bayes and Gibbs sampling in addition to the standard GIZA++ alignments. The submitted tracks are the ArabicEnglish and Turkish-English TED Talks translation tasks.
متن کاملDFKI's system for WMT16 IT-domain task, including analysis of systematic errors
We are presenting a hybrid MT approach in the WMT2016 Shared Translation Task for the IT-Domain. Our work consists of several translation components based on rule-based and statistical approaches that feed into an informed selection mechanism. Additions to last year’s submission include a WSD component, a syntactically-enhanced component and several improvements to the rule-based component, rel...
متن کاملThe tÜBITAK-UEKAE statistical machine translation system for IWSLT 2009
We describe our Arabic-to-English and Turkish-to-English machine translation systems that participated in the IWSLT 2009 evaluation campaign. Both systems are based on the Moses statistical machine translation toolkit, with added components to address the rich morphology of the source languages. Three different morphological approaches are investigated for Turkish. Our primary submission uses l...
متن کامل