In this paper we describe a hybrid approach to Chinese-toEnglish spoken language translation system used for the IWSLT 2006 evaluation campaign. In this system, the phrasebased statistical machine translation (SMT) engine is combined with the template-based machine translation (TBMT) engine and a simple way is proposed to select the best translation from the results generated by the two transla...

Human translators are the key to evaluating machine translation (MT) quality and also to addressing the so far unanswered question when and how to use MT in professional translation workflows. Usually, human judgments come in the form of ranking outputs of different translation systems and recently, post-edits of MT output have come into focus. This paper describes the results of a detailed lar...

Translation validation (TV) is the process of proving that the execution of a translator has generated an output that is a correct translation of the input. When applied to optimizing compilers, TV is used to prove that the generated target code is a correct translation of the source program being compiled. This is in contrast to verifying a compiler, i.e. ensuring that the compiler will genera...

In this paper, the KIT systems submitted to the Shared Translation Task are presented. We participated in two translation directions: from German to English and from English to German. Both translations are generated using phrase-based translation systems. The performance of the systems was boosted by using language models built based on different tokens such as word, part-of-speech, and automa...

In this paper we study geometric versions of Burnside’s Problem and the von Neumann Conjecture. This is done by considering the notion of a translation-like action. Translation-like actions were introduced by Kevin Whyte as a geometric analogue of subgroup containment. Whyte proved a geometric version of the von Neumann Conjecture by showing that a finitely generated group is nonamenable if and...

This study reports an attempt to predict the voice of reference using the information from the input sentences or previous input/output sentences. Our previous study presented a voice controlling method to generate sentences for neural machine translation, wherein it was demonstrated that the BLEU score improved when the voice of generated sentence was controlled relative to that of the referen...

With rapid development of China's railways, there are more overseas construction projects and technical exchanges in the field railway engineering, which have generated widespread demands for translation. To meet increasingly growing translation engineering texts, mode machine plus post editing (MTPE) has been frequently applied besides traditional human (HT) combination quality efficiency. Thr...

We propose a novel multilingual Web crawler and sentence mining system to continuously mine and extract parallel sentences from trillions of websites, unconstrained by domain or url structures, or publication dates. The system is divided into three main modules, namely Web crawler, comparable and parallel website matching and parallel sentence extraction. Previous methods in mining parallel sen...

Introduction: The Dysphagia Handicap Index (DHI) is one of the instruments used for measuring a dysphagic patient’s self-assessment. In some ways, it reflects the patient’s quality of life. Although it has been recognized and widely applied in English speaking populations, it has not been used in its present forms in Persian speaking countries. The purpose of this study was to adapt a Persian v...