Translation quality is one of the key topics in the translation industry today. In 2011, TAUS developed the Dynamic Quality Framework (DQF) in an attempt to standardize translation quality evaluation. In this paper, we will describe common approaches to translation quality and introduce the TAUS framework for QE. We will show that the development of this framework, initiated by the industry, wa...

The market of automated translation quality assurance tools offers quite a limited set of applications with the same well-known functionality as they offered a few years ago. The purpose of this paper is to review the automated translation quality assurance process, to describe several improvements we implemented in Verifika® and to provide measurement of their efficiency. In this paper we will...

The study was intended to provide a description of the attitudes of English-major studentstowards the teaching methods in translation courses to find out more about the relevance andquality of methods to the students’ needs, concerning the necessary educational resourcesprovided in the methods of teaching. Accordingly, a multi-item Likert-scale questionnairecontaining 32 items was developed bas...

In this paper we describe the many steps involved in building a production quality Machine Translation system for translating weather warnings between French and English. Although in principle this task may seem straightforward, the details, especially corpus preparation and final text presentation, involve many difficult aspects that are often glossed over in the literature. On top of the clas...

QT21 (see http://www.qt21.eu/) is an EU-funded project with several goals related to machine translation. This paper relates to the QT21 goal of "improved evaluation ... informed by human translators", using a framework that harmonizes MQM (Multidimensional Quality Metrics) and DQF (Dynamic Quality Framework). The purpose of the paper, which expresses my personal views, is to obtain feedback on...

The usefulness of a translated text for gisting purposes strongly depends on the overall translation quality of the text, but especially on the translation quality of the most informative portions of the text. In this paper we address the problems of ranking translated sentences within a document and ranking translated documents within a set of documents on the same topic according to their inf...

English to Indian language machine translation poses the challenge of structural and morphological divergence. This paper describes English to Indian language statistical machine translation using pre-ordering and suffix separation. The pre-ordering uses rules to transfer the structure of the source sentences prior to training and translation. This syntactic restructuring helps statistical mach...

In this paper we share our experience from implementing machine translation in localization into relatively small languages of the three Baltic countries – Latvian, Lithuanian, and Estonian. We describe our approach in improving terminology translation and consistency by preprocessing of the source text and performing term integration. We present results of a formal evaluation of MT impact on t...

In this paper, we show that retrieval performance for the ImageCLEF bilingual cross language image retrieval task depends upon, among other factors, the quality of query translation. In this preliminary study, we investigate translation quality and retrieval performance using the Systran machine translation system by comparing a manual assessment of translation adequacy with an automatic score ...

We propose a general approach for translating Chinese unknown words (UNK) for SMT. This approach takes advantage of the properties of Chinese word composition rules, i.e., all Chinese words are formed by sequential characters. According to the proposed approach, the unknown word is re-split into a subword sequence followed by subword translation with a subwordbased translation model. “Subword” ...