This paper describes the TU ̈ B ̇ITAK 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 corpus 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.

WedescribetheTU ̈B ̇ITAKsubmissiontotheIWSLT2012 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 Arabic-English and Turkish-English TED Talks translation tasks.

We report on our participation in the IWSLT 2010 evaluation campaign. Similar to previous years, our submitted systems are based on the Moses statistical machine translation toolkit. This year, we also experimented with hierarchical phrase-based models. In addition, we utilized automatic minimum error-rate training instead of manually-guided tuning. We focused more on the BTEC Turkish-English task and explored various experimentations with unsupervised segmentation to measure their effects on the translation performance. We present the results of several contrastive experiments, including those that failed to improve the translation performance.

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 linguistic morphological analysis and statistical disambiguation to generate morpheme-based translation models, which is the approach with the better translation performance. One of the contrastive submissions utilizes unsupervised subword segmentation to generate non-linguistic subword-based translation models, while another contrastive system uses word-based models but makes use of lexical approximation to cope with out-of-vocabulary words, similar to the approach in our Arabic-to-English submission.

We present the TÜBİTAK-UEKAE statistical machine translation system that participated in the IWSLT 2008 evaluation campaign. Our system is based on the open-source phrase-based statistical machine translation software Moses. Additionally, phrase-table augmentation is applied to maximize source language coverage; lexical approximation is applied to replace out-of-vocabulary words with known words prior to decoding; and automatic punctuation insertion is improved. We describe the preprocessing and postprocessing steps and our training and decoding procedures. Results are presented on our participation in the classical Arabic-English and Chinese-English tasks as well as the new Chinese-Spanish direct and Chinese-English-Spanish pivot translation tasks.

We describe the TÜBITAK-UEKAE system that participated in the Arabic-to-English and Japanese-to-English translation tasks of the IWSLT 2007 evaluation campaign. Our system is built on the open-source phrase-based statistical machine translation software Moses. Among available corpora and linguistic resources, only the supplied training data and an Arabic morphological analyzer are used in the system. We present the run-time lexical approximation method to cope with out-of-vocabulary words during decoding. We tested our system under both automatic speech recognition (ASR) and clean transcript (clean) input conditions. Our system was ranked first in both Arabic-to-English and Japanese-to-English tasks under the “clean” condition.