The advantages of machine translation:
- Quick turnaround
- Cost efficient solution for very large texts
- Economical
- Acceptable quality
- Most languages can be catered for
Machine translation (MT) is the fully automated translation of text into another language. MT has improved in recent years, owing to better software and faster computers. Well-known language-industry purchasable MT tools include IBM Watson, MemoQ and DeepL.
It is now possible for computers to learn how words relate to one another and their meaning in different languages. This is achieved using statistical models and artificial intelligence, such as in neural machine translation (NMT). These machines, programmed in specific fields, are quickly able to translate large quantities of usable text.
However, although text translated in this way is understandable, it often feels a little wooden to the reader. Jokes, sarcasm, alliteration and, unfortunately, meaning are often lost. Such a text can also give the reader the impression that your product or service is of inferior quality.
Translations which are intended to persuade the reader should, of course, read well and fit the right cultural context. After all, you want to evoke a positive feeling and achieve results with your text. This is why it makes sense to have machine translation edited by a native speaker of the target language (post-editing or PE).
Many traditional translation agencies are resistant to the emergence of machine translations. Our agency thinks differently. Machine translation is improving every day. Clever application of MT results in major translation-process efficiency gains and cost-savings. However, incorrect use of MT can result in an unusable and unwanted translation. For this reason, human post-editing remains indispensable to the translation process.
Fasttranslator’s approach to MT + PE is explained in more detail below.
We start by comparing your text with our database of manually translated sentences. With over 20 years’ experience, our translation agency has stored hundreds of millions of sentences and their corresponding translations. It is often possible to translate a large part of the text in this first stage.
Then, we start the actual machine translation. The text is translated by a specific NMT engine which has been trained on texts similar to yours or those which match the field of expertise.
Once the text has been translated by machine, professional human translators take over. They check the text for errors, including awkward syntax and incorrect terminology. Most of the time spent on your translation is devoted to post-editing.
Your translated text is now suitable for use in professional communications. The advantages of this combination of MT and human PE are speed, quality and its low price.
To be honest, not every text is suitable for machine translation.
Unsuitable examples are:
Our project managers will immediately advise you whether machine translation is an unwise choice for your particular text or language combination.
Machine translation is well suited for translation of the following examples:
It could be that a translated text does not read well or that a very high-quality translation was required after all. In such cases, we will meet you half way by offering a substantial discount on a 100% human translation.
We hope to have convinced you of the benefits of this translation method. But we can well imagine that you may still have questions about the suitability of your document or text for the machine translation approach. Our team of Project Managers and Account Managers stand ready to answer your questions. You can of course put your questions via our contact form, but if you would prefer to speak to someone on the telephone that is always an option. You’ll find all our contact information on our contact page. Our experts will be happy to advise you about the possibilities. Answers to many queries about our translation services or our translators can be found on our Frequently Asked Questions page.
Estimating the costs of a translation is not always straightforward, and this applies as much to a machine translation as it does to a “normal” translation. Many factors come into play: what are the source and target languages? A translation into French is very likely to be cheaper than putting the same text into Dari. How many words are there in your project? How quickly must the project be completed? You get the idea. Happily though our quotations module allows us to instantly provide a price calculation. So we’d ask you kindly to fill that in.