Sequence to Sequence Neural Machine Translation has achieved significant performance in recent years. Yet, there are some existing issues that Neural Machine Translation still does not solve completely. Two of them are translation of long sentences and “over-translation”. To address these two problems, we propose an approach that utilize more grammatical information such as syntactic dependenci...

Selecting the word translation from a set of target language words, one that conveys the correct sense of source word and makes more fluent target language output, is one of core problems in machine translation. In this paper we compare the 3 methods of estimating word translation probabilities for selecting the word translation in Thai – English Machine Translation. The 3 methods are (1) Metho...

setting standards for translation assessment has usually been problematic for authorities, theoreticians, and most commonly instructors. it is often difficult to tell the difference between translation evaluation, criticism, and assessment due to hardships of bridging the gap between theory and practice. the aim of this study was to create a rubric against which translations could be assessed. ...

Selecting the word translation from a set of target language words, one that conveys the correct sense of source word and makes more fluent target language output, is one of core problems in machine translation. In this paper we compare the 3 methods of estimating word translation probabilities for selecting the translation word in Thai – English Machine Translation. The 3 methods are (1) Metho...

This paper describes a novel method for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The outputs are combined and a possibly new translation hypothesis can be generated. Similarly to the well-established ROVER approach of (Fiscus, 1997) for combining speech recognition hypotheses, the consensus translation is computed by voting on a confusion ...

This paper describes a novel method for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The outputs are combined and a possibly new translation hypothesis can be generated. Similarly to the well-established ROVER approach of (Fiscus, 1997) for combining speech recognition hypotheses, the consensus translation is computed by voting on a confusion ...

This paper describes a phrase-based machine translation approach to normalize Dutch user-generated content (UGC). We compiled a corpus of three different social media genres (text messages, message board posts and tweets) to have a sample of this recent domain. We describe the various characteristics of this noisy text material and explain how it has been manually normalized using newly develop...

Current translation models are mainly designed for languages with limited morphology, which are not readily applicable to agglutinative languages as the difference in the way lexical forms are generated. In this paper, we propose a novel approach for translating agglutinative languages by treating stems and affixes differently. We employ stem as the atomic translation unit to alleviate data spa...

Spi Calculus is an untyped high level modeling language for security protocols, used for formal protocols specification and verification. In this paper, a type system for the Spi Calculus and a translation function are formally defined, in order to formalize the refinement of a Spi Calculus specification into a Java implementation. The Java implementation generated by the translation function u...

This paper reports ongoing experiments towards exploiting the use of images to provide additional context for statistical machine translation (SMT). We investigate whether this contextual information can be helpful in targeting two well-known challenges in machine translation: ambiguity (incorrect translation of words that have multiple senses) and out-of-vocabulary words (words left untranslat...