This paper describes the application of machine translation in overcoming language barriers for global e-commerce at eBay. We look at how buyers are provided the ability to perform cross-lingual search by translation of their search queries into the language of the listed items. We also show the process of translating item titles and descriptions from the inventory language into the user’s pref...

In her article "Challenges and Translation" Kathleen Shields argues that Goethe translation practice: in creating a canon representing the best of each nation, translation occupied centre stage. Nation-building in Europe in the nineteenth century transnational literature where translation as a way of decentering from a strong monolingual base. There are four challenges for comparative literatur...

The paper studies the use of global unobservability constraints in a CNF translation of Boolean formulas, where the unobservability of logic blocks is encoded with CNF unobservability variables and the logic output values of the blocks with CNF logic variables. Each block’s unobservability variable is restricted by local unobservability constraints, expressing conditions that the output value o...

This paper presents experiments with document-level machine translation with readability constraints. We describe the task of producing simplified translations from a given source with the aim to optimize machine translation for specific target users such as language learners. In our approach, we introduce global features that are known to affect readability into a documentlevel SMT decoding fr...

As the global prevalence of obesity and chronic diseases continues to rise, the need for effective health promotion programs is imperative. Whilst research into effectiveness of health promotion programs is needed to improve population health outcomes, translation of these research findings into policy and practice is crucial. Translation requires not only efficacy data around what to implement...

Hierarchical phrase-based machine translation can capture global reordering with synchronous context-free grammar, but has little ability to evaluate the correctness of word orderings during decoding. We propose a method to integrate word-based reordering model into hierarchical phrasebased machine translation to overcome this weakness. Our approach extends the synchronous context-free grammar ...

We address the problem of statistical machine translation from highly inflective language to less inflective one. The characteristics of inflective languages are generally not taken into account by the statistical machine translation system. Existing translation systems often treat different inflected word forms of the same lemma as if they were independent of each other, although some interdep...

We directly investigate a subject of much recent debate: do word sense disambigation models help statistical machine translation quality? We present empirical results casting doubt on this common, but unproved, assumption. Using a state-ofthe-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguati...

We propose a pre-processing stage for Statistical Machine Translation (SMT) systems where the words of the source sentence are re-ordered as per the syntax of the target language prior to the alignment process, so that the alignment found by the statistical system is improved. We take a dependency parse of the source sentence and linearize it as per the syntax of the target language, before it ...