Recently we published updated machine translation (MT) quality comparison. The comparison was made in late August with our fully-automatic award-winning system called MT-Qualifier. We compared MT quality in two language pairs, English to Spanish and English to Portuguese. The results are quite interesting because they contradict a bit with the common understanding of the best services. “A myth is busted”, so to speak. Continue reading MT Quality Comparison: Google Translate vs. Microsoft Translator
Words form sentences and sentences build stories. The story creates a context to the individual words. Words are only details. This concept is easy to understand for us human beings. For machines it is too complicated. Machine translators know which words mean the same thing in different languages but they still aren’t able to understand whole stories. They have difficulties in seeing the forest for the trees. Continue reading Context Is Machine Translator’s Weak Point
Although machine translation (MT) isn’t an answer to all our translation needs, MT can ease our lives remarkably. Even the imperfect quality isn’t an issue when the situation doesn’t require faultlessness. The key factor is to know what kind of translation is needed. Professional translators produce the best quality but MT can help you with other translation needs. Continue reading When to Use Machine Translation
Machine Translation (MT) is a fantastic innovation. It helps people to communicate with each others. With MT people have all the online knowledge just few clicks away. The best thing is that MT is fast and everyone has a free access to at least few machine translation services. It seems like MT is the answer to all our linguistic dilemmas. Continue reading What NOT to Do with Machine Translation
Machine translators work impeccably. They don’t make mistakes. They are perfect in their core competencies. However, what people often forget is that machine translators’ skills are purely mathematical. When an automatic translation is involved in some sort of problematic situation the machine can’t be held responsible. The user has made the decision to use and publish raw machine translation without post-editing. The machine is only a tool.