The gold standard for measuring machine translation quality is the rating of candidate sentences by by experienced translators. However, automated measures are necessary for rapid iterative development. BLEU (Papineni et al. 2002) is the best-known automatic measure of translation quality. BLEU and related measures are used to automatically evaluate machine translation (MT) systems, as well as ...

this paper aims at describing the mechanism of german loanwords adaptation with respect to constraints of persian language and within ot framework. consequently the adaptation of consonant clusters and diphthongs as well as the phonemes substituted in loanwords will be examined. prince and smolensky’s (1993) optimality theory with its key notions of faithfulness and markedness constraints is su...

Traslán makes full use of MT during our translation workflow, where the raw output from our Machine Translation (MT) system is passed onto human translators who perform post-editing (if necessary) to arrive at the final translation. Within Traslán we have found that using MT has enabled us to increase the speed, accuracy and consistency of translation elements which allow us to process larger a...

In human translation, translators first make draft translations and then modify and edit them. In the case of experienced translators, this process involves the use of wide-ranging expert knowledge, which has mostly remained implicit so far. Describing the difference between draft and final translations, therefore, should contribute to making this knowledge explicit. If we could clarify the exp...

WIPO has developed its own MT tool, initially based on open-source Moses (phrase-based SMT PBSMT), more recently based on open-source for Neural Machine Translation (NMT), namely Nematus and AmunMT. The PBSMT tool, trained on different documents, has been successfully installed in the UN (United Nations) and in other international organizations (ITU, IMO, FAO, WTO, ILO, WTO, TGF and FAO). The t...