Attempts to estimate phrase translation probablities for statistical machine translation using iteratively-trained models have repeatedly failed to produce translations as good as those obtained by estimating phrase translation probablities from surface statistics of bilingual word alignments as described by Koehn, et al. (2003). We propose a new iteratively-trained phrase translation model tha...

Machine translation (MT) systems are now ubiquitous. This ubiquity is due to a combination of increased need for translation in today's global marketplace, and an exponential growth in computing power that has made such systems viable. And under the right circumstances, MT systems are a powerful tool. They offer low-quality translations in situations where low-quality translation is better than...

This paper describes the recurrent neural network based model for translation quality estimation. Recurrent neural network based quality estimation model consists of two parts. The first part using two bidirectional recurrent neural networks generates the quality information about whether each word in translation is properly translated. The second part using another recurrent neural network pre...

Deepfix is a statistical post-editing system for improving the quality of statistical machine translation outputs. It attempts to correct errors in verb-noun valency using deep syntactic analysis and a simple probabilistic model of valency. On the English-to-Czech translation pair, we show that statistical post-editing of statistical machine translation leads to an improvement of the translatio...

This paper reports the first results of an on-going research on evaluation of Machine Translation quality. The starting point for this work was the framework of ISLE (the International Standards for Language Engineering), which provides a classification for evaluation of Machine Translation. In order to make a quantitative evaluation of translation quality, we pursue a more consistent, finegrai...

We introduce alignment models for Machine Translation that take into account the context of a source word when determining its translation. Since the use of these contexts alone causes data sparsity problems, we develop a decision tree algorithm for clustering the contexts based on optimisation of the EM auxiliary function. We show that our contextdependent models lead to an improvement in alig...

We present a study of aspects of discourse structure — specifically discourse devices used to organize information in a sentence — that significantly impact the quality of machine translation. Our analysis is based on manual evaluations of translations of news from Chinese and Arabic to English. We find that there is a particularly strong mismatch in the notion of what constitutes a sentence in...

This paper presents the results of the WMT14 shared tasks, which included a standard news translation task, a separate medical translation task, a task for run-time estimation of machine translation quality, and a metrics task. This year, 143 machine translation systems from 23 institutions were submitted to the ten translation directions in the standard translation task. An additional 6 anonym...

To achieve translation technology that is adequate for speech-to-speech translation (S2S), this paper introduces a new attempt named Corpus-Centered Computation, (abbreviated to C and pronounced c-cube). As opposed to conventional approaches adopted by machine translation systems for written language, C places corpora at the center of the technology. For example, translation knowledge is extrac...

We intended to demonstrate the effect of using N -best speech recognition hypotheses for improving speech translation performance. A log-linear model, which integrated features from speech recognition and statistical machine translation, was used to rescore the translation candidates. Model parameters were estimated by optimizing an objectively measurable but subjectively relevant translation q...