Translate

Translating corporate language with AI

Unlimited number of users

Easy integration into editorial systems

High availability of services

Data Protection & Data Security

Adaptability to the company

Team session in between CMS editors from different countries using wonk.ai

Translate

Translating corporate language with AI

Use existing corporate knowledge and translations.

Use available websites, documents – perhaps even a translation memory system – as a training ground for machine translation.

Train your own language models – with a clear evaluation basis and crisp process.

All in corporate language and in real time.

What can Translate do?

Translate combines the economics of machine translation with the quality of human translation.

Website Projects and Content – . XLIFF

.xml, .xlif and other formats that a CMS can export, Translate avoids and translates the language true to format.

Glossaries & Stop-Words

For ad-hoc changes, Translate offers glossaries and Stop-Word maintenance. Glossaries hold word equivalents in the respective language, similar to a dictionary. Stop words are used to not translate proper names and product names.

Office documents – Word, Excel, PowerPoint

Classic documents that arise in daily office work can be translated with Translate. And keep your formatting and design.

Initial training in own company language

At the beginning of the collaboration, we train Translate based on your existing content from websites, translation memory systems (TMS), documents of any form and existing glossaries.

Downloads & print templates – .PDF files

Use transate for already completed documents in the format .pdf and translate them into the desired languages while retaining formatting and layout.

Training Data Storage & Continuous Learning

Via the API and the web frontend you have the possibility to make adaptations and improvements to the translations. With your proofreading, your company translations are improved with every training.

Catalogs, brochures and printed matter – .IDML

This content is usually generated in Indesign in the format .idml. Translate translates the content so that you are editable and preserved in indesign format. 

100% DSVGO compliant

Integrated through API into Microsoft Azure. Data in EU & Germany – or on-premise if desired

But – there are existing solutions.

Companies have translation processes and solutions,  but that doesn’t mean they’re good.

– Time-to-market – Translation takes weeks
– Quality – The translation results are not good enough
Efficiency – The translation process is very manual with it’s many  media disruptions
– Costs – Translations are too expensive at €0.15 per word

We can do better. 

The quality of previous translations with the efficiency of machine translation.

+ 50% faster time-to-market
+ 80% lower costs
+ 70% better quality

How is this possible? 

By training machine translation in your corporate language. 

Collection – Collect language data from websites, glossaries, language databases, documents, TMS exports
Extraction – extracting the language pairs from the collected data
Processing – Validating, cleaning and processing the language data for the trainings
AI-TrainingTraining the language models on translation knowledge
Evaluation – Evaluation of the language models by the customer in the model blind test

Training of corporate language models.

Translate learns your corporate language.

What the training can do:

Learning the company’s special terms, tonality and proper names – for the highest translation quality
Continuous learning and improvement in operations
Processing of all data sources for training – whether websites, TMS, glossaries, documents or other sources

Who uses Translate?

Translate supports medium-sized businesses and corporations in their internationalisation.

KWS Saat SE & Co. KGaA

Stock-exchange listed plant breeding and biotechnology company.

The world’s fourth-largest seed producer by revenue from agricultural crops.

Revenue: EUR 1.54 billion (2021–2022)

Employees: over 5000

70 countries

MULTIVAC GROUP

MULTIVAC is a solution provider for the packaging and processing of foodstuffs, medical and pharmaceutical products as well as consumer and industrial goods of all kinds.

Revenue: EUR 1.37 billion (2022)

Employees: 7000

84 locations, 160 countries

Phase Plan Training & Operations

From data to translation

01

Data exchange

wonk.ai will receive the list of languages to be translated and access to the data sources available for training.

02

Data Checkup

wonk.ai checks the quality of the language data and the number of language pairs to be achieved and provides feedback on feasibility.

03

Specifying the testers

The client determines which stakeholders and experts in the company will review the language models and evaluate the results – compared to previous translations or alternative solutions.

04

Training of language models

wonk.ai extracts the language data, validates and cleans the training set, and trains the language models with mathematical evaluation.

05

Evaluation of the results

The customer’s testers evaluate the language models within their own assessment environment and provide feedback on individual results.

05

Commissioning

Once the language models have been initially approved, they can be put into operation directly and can be used via the customer’s own web environment. The trained models can also be integrated into third-party systems via the API and can thus be used in the entire system landscape.

Save Rate

> 80%

Training corporate language

Saves time and money and enables relaunch

How much does relaunching the websites  with translators cost compared to wonk.ai?

Please enable JavaScript in your browser to complete this form.
Ausgewählter Wert: 1000000 Wörter
Ausgewählter Wert: 5 Sprachen
Ausgewählter Wert: 0.15 Euro

Sollen wir Dir die Berechnung zusenden?

HOW MUCH DOES IT COST TO RUN TRANSLATE for companies?

Save up to 80%

FAQ – Questions & Answers

We are happy to answer any questions you may have in our personal get-to-know-you meetings.

If you’re in a hurry, here are some questions we’ve been asked.

Yes. It is also possible to operate our services on-premise in your own infrastructure.

By default, we operate our services in a Microsoft Azure cloud architecture. Fully encrypted and only accessible to the company.

There are also IT departments that want to run our models in their own cloud (private cloud) such as Microsoft Azure Cloud, AWS or Google Cloud. This is possible, but requires a lot of work on the project.

It is also possible to operate completely on-premise in the company’s own data center, which requires a one-time project effort, an analysis of the use cases and the corresponding hardware with GPUs for hosting.

So far, we have covered 50 different languages in our projects. We are able to deliver well over 100 languages in high quality. We are happy to receive a list of the desired language pairs and give a concrete statement on the subject of the project.
Through our API architecture, we have ensured that your models can be connected quickly and reliably in all relevant systems. Connections implemented so far range from content management systems, e-shops, product information systems to office software such as Word and Excel.

Of course, with our separate web frontend, you always have the opportunity to use the functionalities and your models across systems.
To train the language models, we extract sentence pairs in the source and target languages.

We obtain these pairs of sentences from the existing publications on the company’s websites, from publications, databases, translation memory systems, glossaries and much more.

We are able to process a wide range of formats and data and make them usable for training.
Most companies have enough language data from the past for training.

We can collect this language data and make it usable.

Through our processes, we are usually able to win 10,000 to 300,000 sentence pairs per language.

In the training projects, we check at the beginning for which languages enough training data are available and communicate the status early, so that transparency is available from the start.
The quality of translations and their improvement can be calculated and expressed mathematically. Of course, we deliver that.

In our experience, the acceptance of specialist departments, countries and translators is more relevant.

That’s why we’ve created an evaluation environment where your company’s employees can test and evaluate the trained models.

Compared to the previous manual translations and also compared to other untrained generic translation services. The qualitative evaluation by your colleagues is then the basis for deciding which trained models are ready for translation.
Translation memory systems are designed to help translators and language managers deliver consistent translation quality. Weiterhin sollen TMS die Übersetzungskosten reduzieren, da bisher schon übersetzte Zeichenketten nicht neu an die Übersetzung gegeben werden.  Stattdessen wird, bei entsprechender Übereinstimmung der Zeichen, die schon übersetzte Zeichenkette der Vergangenheit zurückgegeben.

This should help reduce translation costs and keep translation quality constant. And this approach makes sense when many manual and changing translators work with the knowledge.

wonk.ai language models combine the previous translation knowledge (like a TMS) with the feedback of the proof readers. This makes a translation memory system unnecessary for many use cases.

The price of translations depends on the number of words to be translated per year. The cost per word starts at €0.03 for 600,000 words per year.

The number of words is available in the company for the entire duration of the contract.

There is a 10% goodwill allowance for over- or under-consumption of words. If this goodwill corridor is exceeded within the term of the contract, the remaining amount will be credited or invoiced on the basis of the agreed price per word and after deduction of goodwill.

Machine translation is always useful when many translations in many languages are needed in a short period of time.

This is the case, for example, when global content campaigns are to be rolled out or when changing CMS and relaunching websites. Whenever a lot of new content is created or edited and is to be translated in a short time, machine translation is particularly useful.

For assessment:
A typical rollout project as part of the website launch, with 400 content pages per language and 10 languages into which is translated – 2,000,000 words (2 million – sic) – requires a significant volume that makes sense for support.

Absolutely. With wonk.ai you can translate .pdf files conveniently and quickly.
Various file formats can be translated either via the API or directly via the web frontend with drag-and-drop. .pdf format and many more.

Automatic translation also works for classic Office files (Powerpoint, Excel, Word) as well as for specific formats, e.g. InDesign prepress.

Our customers

How about it?

Automate your translations in high-quality.

Translate

Trained Translation Models

Continuously learning AI models for real-time, professional-quality translations.

Training

of models

Your previous translations are a treasure trove of data that you should use to your advantage. 

Quality

Significantly better

How powerful is a trained model compared to a generic model?

Customers

Contentment

Translate supports medium-sized companies and corporations in their internationalization