From time to time we find ourselves in situations in which it would help to understand a foreign language: before the holidays, when you want to negotiate the last details of the holiday home with the landlord; at work, when you receive an inquiry from abroad; at home, when a new device or gadget only comes with a manual in an undecipherable language.

In such cases, the online service of a company from Cologne, Germany can help: DeepL translates texts almost as well as a human being. This article will show you how incredibly well this works.

What makes translations so difficult?

Many translations are bad because they come directly from the computer: Automatically translated instruction manuals are full of errors ("associate the air pump with the mattress"); many instant noodle recipes are incomprehensible gibberish.

But it doesn't have to be that way: The German translation service DeepL analyzes texts so thoroughly that it can avoid misunderstandings. Sometimes DeepL reaches almost the quality of a human translator.

The main problem with translation between languages is that the meaning of many words depends on their context. Two examples from the English language: "sanction" can either mean "approve" or "penalize", and "oversight" is the noun form of two verbs with contrary meanings: "oversee" and "overlook". These need to be translated differently to other languages. For example, "sanction" could either be "billigen" or "bestrafen" in German, and "oversight" would either need to be translated as "Aufsicht" or "Versehen". Very few computer translators are able to tell which one is the right one.

Advantage through neural networks

DeepL analyzes texts with neural networks. Neural networks, sometimes also a bit pompously referred to as "artificial intelligence", solve problems on the basis of predefined patterns. When a neural network is trained to translate, it is first "fed" with correct existing translations. It links these together until it can deduce from them how new texts are to be translated. This method is also called "machine learning".

The learning effort of a neural network is quite large. For example, DeepL relies on a supercomputer with a performance of 5.1 PetaFLOPS – which corresponds roughly to the processor performance of 5000 desktop computers. The DeepL mastermind is not located in Germany, but in a data center in Keflavik, Iceland. Over there it is easier for the translation program to keep a cool head: low outside temperatures on the Atlantic island make the air conditioning of the data center easier.

The secret recipe for better translations

The online translation tools from Google ("Google Translate") and Microsoft ("Bing Microsoft Translator") also rely on neural networks. However, their results are far from the quality of the German newcomer. Texts translated by DeepL sometimes appear not just human, but even elegant.

How do the developers from Cologne achieve this? The company keeps mum and just lets out that its self-developed "new arrangement of neurons and their connections" better reflects natural language than previous translation systems.

Unlike the competition, DeepL offers a limited language selection. The system was launched in 2017 with seven languages: German, English, French, Italian, Dutch, Polish and Spanish. Portuguese and Russian were added in December 2018, and the manufacturer says that Japanese and Mandarin Chinese are in preparation. For comparison, Google currently offers 99 languages to choose from.

How to get the most out of DeepL

DeepL can be used free of charge and without registration. You either copy the text to be translated into an online form or upload it as a text document or presentation. The form field accepts a maximum of 5000 characters, and there is no size limit for uploads.

The big advantage of translating via the form is that you can refine the result interactively. If you notice a bumpy translation, clicking the translated text opens a pop-up menu with alternative suggestions. This allows the translation to be corrected quickly and easily. DeepL not only corrects individual words: if necessary, the translator proposes a completely new sentence.

DeepL also accepts DOCX text documents and PPTX presentations. In TextMaker, go to File | Save as and save the document in the file format "Microsoft Word 2007-2019 (*.docx)" before uploading it. In SoftMaker Presentations, save your file in the file format "PowerPoint 2007-2019 document (*.pptx)". Then use your mouse to drag the file from the Windows File Explorer to the form field on the DeepL website.

The free version, however, returns read-only documents from which you can only copy the raw text. Also, it is not possible to correct the translation interactively with uploaded files.

A German competitor for Google, Microsoft & Co.

We had a total of seven online translation tools translate the same text from English; DeepL was far superior to all its competitors. The following were tested:

  • Babylon Next Generation (NG)
  • DeepL Translator
  • Google Translator
  • Bing Microsoft Translator
  • Promt Online Translator
  • Systran Text Translation
  • WordLingo Free online language translator

The comparison took place on the same day in April 2019.

Some results confirmed common clichés about computer translations: Who could reconstruct what "His a fine book therein allows him is own way" used to mean? Other online translation tools shocked with gross mistranslations. For example, one of the tools once inexplicably mistook "punctuation" for "punctuality". Several services left essential parts simply untranslated – without any warning or error message.

Babylon NG, Systran and WordLingo produced the weakest results. Babylon always processes only one single paragraph and partially produced heavily outdated German. Systran was horribly wrong in several translations. WorldLingo left several words untranslated and produced extremely long, hard to understand sentences. Promt worked a bit better, but still rather produced gibberish than usable German.

Bing Microsoft Translator did well, but overall lagged well behind the Google translator. Similar to DeepL, Google offers the possibility to select an alternative translation by clicking on a sentence. However, Google Translate will replace the whole sentence with a different translation. In our test, this led to new errors.

DeepL beat all competitors by a wide margin and could not be tripped up by deliberate spelling mistakes. After two or three clicks in the translation, the text was as well translated as a human translator would have done. For the English-German translation, DeepL was also the only tool to correctly adjust the order of the punctuation marks.

DeepL for language professionals

Especially for technical translations, DeepL means enormous time savings. DeepL offers professionals a paid subscription in three price categories. For professional translators, the most important advantage of the subscription is the data protection.

The free version of DeepL stores all uploaded texts and their translations to train the neural network. The uploads of paying users, on the other hand, are immediately deleted from the servers. In addition, the Pro version returns unprotected documents and presentations and also accepts plain-text (.txt) files. The "Starter" rate includes five document translations per month, "Advanced" includes 20 and "Ultimate" 100 documents per month.

Starting with the Advanced version, DeepL can also be integrated into professional translation tools ("CAT tools", computer-aided translation), such as SDL Trados Studio and memoQ. Software developers can also integrate DeepL translations in their own products by using the DeepL programming interface and pay by translation volume.

Make sensible use of DeepL

For private users who only translate texts occasionally and have no problem storing the texts on the DeepL servers, the free version of DeepL is currently the most attractive solution on the market. Sensitive personal data such as ID numbers, bank details or flight data should be removed from the text before uploading and later be added again manually.

If you need to translate between languages that DeepL does not support yet, the only viable options are Google Translate and Bing Microsoft Translator. Their translations can be very bumpy, but these services also translate entire web pages without having to copy them into the translation field. When you send an automatically translated letter or e-mail, you might want to mention that it has been translated by machine and ask for leniency.

We hope that we have given you a good overview of the current state of online translation tools and look forward to your feedback. Do you already use automatic translation tools in your everyday life? Share your experiences with us – the comments section is open!

Comments  

Deep L is the best on the market: a document of 35 pages from English to German was done in less than 10 minutes. all formats were kept proper in the translated word form, Total 4 or 5 mistakes within the text. I love it.
I've been using DeepL at work for years and have to say that it is the most precise in it's translations and suggestions than any other service. I hope what's written here about Japanese and Mandarin language support is true and that they will achieve it to be as excellent as the English translations are. Also really happy about the fact that a small, say independent company has one up above Microsoft and Google. Their translation services are horrendous and people should consider using dictionaries if not DeepL instead of them.
Very good and informative write up on translation engines. I use Matecat as both a CAT and translation engine provider, but unfortunately it doesn't integrate with DeepL at the moment.
Good Information About Translation.
thank you for this very valuable info!
By far the best translator in the market.
best results can be achieved to open the translator twice and check the reverse translation. This allows perfect selection of the proposed alternatives...
I cannot imagine any good reason to place in my home an always-on listening device that enables lurkers anywhere in the world to listen to what I say or do. It astounds me that so many individuals are so ready and willing to sacrifice their privacy in exchange for . . . what?
I use the app Telegram for most of my communications in text since it is, by all accounts, as secure as is possible with everything encrypted in the cloud and peer to peer text can also be selected if required for extra security. it also offers encrypted telephone calls over the Internet that are for the most part superior in sound quality to using a cellphone network subscription. in Telegram I often get stray messages in other languages that I sometimes follow up out of curiosity and find I can have quite a decent discussion in real time because as soon as I highlight (block in the old parlance) the foreign text a handy 'translate' popup notice appears in the upper right hand corner of telegram. this I can paste directly into google translate and is instantly translated into my language. after reading this in my language I can write a reply and it will be translated back into the foreign language blocked with CTL+A and pasted (with a mouse click in Debian Linux) immediately at the cursor in Telegram.

from the replies I've received some think I can speak their language, so good is the translation, especially if the language is Spanish, or Italian, not so much so French and German and the comments become derisory if I translate my answer into Persian. It would be good to advance to DeepL someday if a helpful app were to be developed that worked with clever and thoughtful software like Telegram so the transfer to the great AI on ice in Iceland did not have to be in a microsoft office .docx file extension.
And for professional work, you can always hire a professional to provide you with a translation (evreeb@netscape.net)
Das ist alles schön und gut, da ich für mich bin, bis er Ungarisch kann
I have just tried Deepl on the foreword of the Langenscheidt Pocket Dictionary English to German and German to English. The foreword is published there in both langauages, good English and (I think, but I am English) good German.

Two years ago I tested Microsoft Translate from German to English. The result was very weak. Deepl today was very good: better than the average schoolchild but with small weaknesses that a discerning reader will notice. Deepl is a huge improvement.
A very timely article! My wife and I have not long ago moved from Australia to Spain, so a translator is indispensable. Will definitely be giving this a try. Cheers!
Apparently it will not translate a photo of text. I have a photo of an old German obituary that I would like translated to English. I tried but seemed it would not accept the photo. Maybe I can try to convert the photo of the text to an actual text document. I'll work on that.
To translate it, you must first convert the text on the photo into editable text. Afterwards, you'll be able to enter the text in the translation input field via copy & paste. Maybe the OCR feature of our PDF editor FlexiPDF can help you converting the photo to editable text.

You can find a free trial of FlexiPDF 2019 at https://www.softmaker.com/en/flexipdf-download
Thank you for your valuable research and information on translators, especially DeepL.
Very informative!
Very informative. I have saved this article to Pocket, and will use it often. Thank you!
Thanks for the informative article - happy to learn about this new tool - it looks excellent!
I concur unreservedly with Gerald's conclusions. DeepL is a gift from the gods.
The biggest problem I find with online translators is that they cannot determine whether you are using formal or informal for second person addresses (e.g. tu vs vous in French), so they always default to formal. Unfortunately, DeepL seems to be no better at this than Google.
Thank you for your comment. Of course, there are still situations where automatic translation tools reach their limits. In such cases it is still helpful to have a basic understanding of the target language to make make manual corrections.
That's exactly what I had to do. One of my connections is another [fiction] writer. Since I'm fluent in English and German, the latter is my mother tongue, she asked me for editing a German translation, done with DeepL

The original was a well selling non-fiction eBook published in English. I had done some work for her in the past and can compare.

Bottom line is, it took about four weeks less to polish up the existing AI translation, compared with doing the whole translation from scratch.
But that's a problem inherent to any "translation". It's frankly just impossible for any translator - computer-based or human - to interpret and express different levels of linguistic formality between languages that don't have "equivalent" words, without much more context than is present from the face of most texts themselves.

It's relatively straightforward to translate between, say, German and Spanish, since both languages have an "informal you" that is used in much the same ways. But unless English speakers start using "thou" and "ye" and their associated verb and pronomial forms, there is just no way to determine the formality of "you" from the face of an English-language text. And the task becomes vastly more complex when the languages involved have no linguistic "familial" relationship at all... (like Japanese and English, to cite just one obvious example).
Excellent information. Thank you!

Add comment