No doubt, this is the most beloved automation we have. Introducing automatic machine translation to your workflow is a real game-changer, precisely in line with our vision of as automated localization as possible.

We consider translation quality an important factor, and that's the reason why our Continuous Localization Team can automate professional human translation.

However, machine translation can be enough for quick prototyping or less important texts - such as descriptions or error messages that are rarely (or never for perfect software 😄) seen.

So, let's dive deeper into a theoretical situation when we are translating an e-commerce website. While product titles are subject to extra (human) care, we don't care that much about descriptions. However, let's assume that we still want them to be checked by human reviewers after they are translated by machine.

🤓 1. Configure the project to publish unapproved translations 🔗

There is a small option hidden in the project settings, which is a true gem. It can be used in different workflows to shorten the delivery time of your localized product or service.

Navigate to Project Settings > Publishing and look for Publish unapproved translations for selected languages. By default, Localazy only publishes approved translations, but for languages listed there, the latest unapproved version is published if there is no approved version.

article-image

This setting is extremely handy in our situation. We are about to create a workflow to translate our texts automatically into German, French, and Spanish, and we want the translations to be available for download. However, at the same time, we want them to go through the review process for human checks. And that's exactly where publishing unapproved translations is the right tool to use.

🚀 2. Create and configure a new workflow 🔗

Once the publishing of unapproved translations is configured, navigate to Workflows in the console and select the project you want to automate. Now, create a new empty workflow. You can name it however you want; I chose Pre-translate with DeepL, so it's descriptive.

article-image

My new workflow is ready, but it's empty and stopped, let's edit it.

Be sure to enable the workflow, as they are disabled by default for security reasons. Also, select the desired action, which is Pretranslate using MT engine.

article-image

Action Configuration 🔗

The action we selected above comes with a detailed configuration. Let's assume we want to translate our uploaded texts quickly into German, French, and Spanish. We also want to review all the MT translations so they are required to go through the review process (Send translations to the review process).

Another option is also important for us - whenever we change the text, we want it to be quickly translated by MT again (Apply to translations in the source changed state).

article-image

Trigger Events 🔗

We want to trigger the event if new keys are added or old keys are updated either through CLI, API, or manually, so out of the possible Trigger Events, we need the Key or translation uploaded, the Key or translation updated, and the Key created manually.

article-image

Filters 🔗

Let's dive into the filters, which is another exciting part of the configuration process.

As pointed out at the beginning of this article, we run an e-commerce site and only want descriptions to be translated using the MT engine. Let's untick Apply to all events and add a simple content filter to match all the keys ending with .description (assuming that our key naming pattern is product.XXX.description for descriptions).

article-image

🖍️ 3. Add or upload keys 🔗

After you hit the Save Changes button, the setup is done. Now, you can just add or upload keys and wait for magic to happen. The uploaded keys will be automatically processed by the workflow we just created, which means that DeepL will take care of them, while Localazy will ask you to review them later but, at the same time, publish the unapproved translations.

Automated MT pretranslation and publishing of unapproved translations are a match made in heaven.

✔️ Conclusion 🔗

While it would make sense, for many scenarios, to just translate all the content using the machine translation engine, at Localazy, we have decided to go a bit more complicated way with workflows as they are flexible and can adapt to any possible use case you may have.

Combining automatic MT translations with publishing them, even if unapproved, is the way to get them out quickly and still retain control over their quality.

Learn more about Automated Workflows in the documentation.