In the globalization era, some translation scholars are of the belief that the ongoing process of globaliza- tion among different and diverse languages and cultures brings about incomprehensibility in translation products. By contrast, some others believe that the globalization trend leads to comprehensible transla- tions. The present research investigates the comprehensibility of the Per...

This paper discusses the acceptability of Near Human Quality machine translation. It defines Near Human Quality and provides examples of cases where Near Human Quality machine translation is acceptable. The paper assumes that there are programs capable of generating Near Human Quality output after some customization. The purpose of this paper is to discuss the acceptability of Near Human Qualit...

Description The need for quick-turnaround, high-volume machine translation (MT) projects continues to grow in the localization industry. There is a wide range of quality requirements not only across different clients, but often within a single client across different content types (sales & marketing materials, user-generated content, website content, user manuals, etc.). Most clients have style...

Machine translation (MT) is most often used for texts of publishable quality. However, there is increasing interest in providing translations of user-generated content in customer forums. This paper describes research towards addressing this challenge by automatically improving the quality of community forum data to improve MT results.

Post-editing is commonly performed on computer-generated texts, whether from Machine Translation (MT) or NLG systems, to make the texts acceptable to end users. MT systems are often evaluated using post-edit data. In this paper we describe our experience of using post-edit data to evaluate SUMTIME-MOUSAM, an NLG system that produces marine weather forecasts.

This paper describes a range of automatic and manual comparisons of phrase-based and syntax-based statistical machine translation methods applied to English-German and English-French translation of user-generated content. The syntax-based methods underperform the phrase-based models and the relaxation of syntactic constraints to broaden translation rule coverage means that these models do not n...

The poor quality of user-generated content (UGC) found in forums hinders both readability and machine-translatability. To improve these two aspects, we have developed humanand machine-oriented pre-editing rules, which correct or reformulate this content. In this paper we present the results of a study which investigates whether pre-editing rules that improve the quality of statistical machine t...

A major challenge for statistical machine translation (SMT) of Arabic-to-English user-generated text is the prevalence of text written in Arabizi, or Romanized Arabic. When facing such texts, a translation system trained on conventional Arabic-English data will suffer from extremely low model coverage. In addition, Arabizi is not regulated by any official standardization and therefore highly am...